© 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. 73274
    Prev
    Next
    INDEX
    Explanations

    method calls with specific contexts

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

    The neuron fires on identifier tokens that are used as parameter (or local variable) names in function or method signatures.

    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
    を
    -1.42
     hongos
    -1.38
     tristes
    -1.32
    Films
    -1.27
    rump
    -1.27
     vacas
    -1.27
    ducks
    -1.24
    และ
    -1.23
    ！！
    -1.23
     mortes
    -1.23
    POSITIVE LOGITS
    F
    1.54
    必要があります
    1.42
    R
    1.39
    \_
    1.31
    必要がある
    1.29
    le
    1.29
    V
    1.28
    u
    1.27
    譏
    1.27
    d
    1.21
    Activations Density 0.007%

    No Known Activations