© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58138
    Prev
    Next
    INDEX
    Explanations

    normal honeybee, some T cells, those giant planets

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron activates for articles or words that introduce a specific entity or category in academic, scientific, or news text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects general non‐specific qualifiers and quantifiers (e.g. words like “some,” “multiple,” “other,” “normal,” and “those”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preuves
    -1.13
     déclarations
    -1.05
     cession
    -1.01
    agosto
    -0.99
     témoignages
    -0.99
    Примеры
    -0.96
     démarrage
    -0.96
     ouvrage
    -0.94
    כנס
    -0.94
     mauvaises
    -0.93
    POSITIVE LOGITS
     issues
    2.27
     considerations
    2.17
     criteria
    2.17
     requirements
    2.16
     advantages
    2.16
     reasons
    2.14
     strategy
    2.14
     idea
    2.14
     problems
    2.13
     situation
    2.09
    Activations Density 0.377%

    No Known Activations