© 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. 10-GEMMASCOPE-RES-131K
    7. 7168
    Prev
    Next
    INDEX
    Explanations

    programming identifiers

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

    The neuron consistently lights up on identifiers introduced as function or method parameters (i.e. the names of arguments in 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_10/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
     and
    -2.34
    halloween
    -1.37
     Elected
    -1.32
    ekk
    -1.31
    GetKeyDown
    -1.30
    шать
    -1.25
    และ
    -1.24
    ouncements
    -1.23
     kolik
    -1.23
     jöv
    -1.23
    POSITIVE LOGITS
    lla
    1.26
    ệu
    1.25
     was
    1.23
     „
    1.22
    mability
    1.20
    過了
    1.19
     fatiga
    1.19
    䛗
    1.19
     izquierdo
    1.18
    urization
    1.18
    Activations Density 0.018%

    No Known Activations