© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28108
    Prev
    Next
    INDEX
    Explanations

    specific identifier or variable

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

    This neuron fires on code identifiers for functions or methods (typically capitalized or ALL_CAPS names) marking the start of a function/method call or definition.

    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
     lindos
    -1.08
     nových
    -1.05
     informaci
    -1.05
     sebagainya
    -1.04
     höl
    -1.04
     Alkohol
    -1.03
     poivre
    -1.03
     blusa
    -1.02
     coloridos
    -1.02
     Aqui
    -1.02
    POSITIVE LOGITS
     individual
    1.26
     specifically
    1.13
     einzel
    1.07
    individual
    1.01
    U
    0.98
    id
    0.98
    個別
    0.97
    No
    0.97
    At
    0.96
     непосредственно
    0.95
    Activations Density 0.004%

    No Known Activations