© 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. 107985
    Prev
    Next
    INDEX
    Explanations

    public method names

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

    The neuron strongly activates on Java package/import declarations and fully‐qualified type or service identifiers.

    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
    昭和
    -0.82
    স
    -0.77
    cellaneous
    -0.77
    iliares
    -0.76
    メートル
    -0.76
     funções
    -0.76
    ░
    -0.75
    🌾
    -0.75
    Vegeu
    -0.73
    ❞
    -0.73
    POSITIVE LOGITS
     age
    1.28
     name
    1.13
     aged
    1.09
     ages
    1.08
    年齡
    1.00
    getName
    0.93
     say
    0.93
     boys
    0.92
     Age
    0.91
    SAY
    0.91
    Activations Density 0.017%

    No Known Activations