© 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. 22-GEMMASCOPE-RES-131K
    7. 26642
    Prev
    Next
    INDEX
    Explanations

    future intentions and applications

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

    This neuron activates on content‐bearing tokens—especially nouns and verbs carrying domain‐specific or technical information—rather than on common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     burbu
    -0.93
    ମ
    -0.93
     vekt
    -0.91
     geene
    -0.87
     papir
    -0.85
    bentuk
    -0.84
     kuni
    -0.83
    liai
    -0.82
    itaria
    -0.82
     broder
    -0.82
    POSITIVE LOGITS
     so
    1.38
     need
    1.33
    これで
    1.20
     want
    1.18
     helps
    1.16
     wanted
    1.13
     needed
    1.09
    ต้องการ
    1.00
     help
    1.00
     lets
    0.98
    Activations Density 0.103%

    No Known Activations