© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76693
    Prev
    Next
    INDEX
    Explanations

    description and documentation metadata

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

    The neuron strongly activates on code‐structure punctuation—especially colons, commas, “=>” arrows, and similar tokens used in function/type signatures and parameter lists.

    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
    outen
    -1.00
     stipulation
    -0.90
     запе
    -0.88
     militari
    -0.85
     Singapura
    -0.85
    Recall
    -0.83
    falz
    -0.83
     stipulations
    -0.82
     Públicas
    -0.81
     Palacio
    -0.81
    POSITIVE LOGITS
     requires
    1.37
     documentation
    1.30
     require
    1.18
     category
    1.15
     short
    1.12
     requiring
    1.11
     description
    1.09
     needs
    1.02
     can
    1.00
     help
    0.98
    Activations Density 0.079%

    No Known Activations