© 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. 10-GEMMASCOPE-RES-131K
    4. 47902
    Prev
    Next
    INDEX
    Explanations

    code definitions and statements

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

    The neuron fires on variable or field identifiers in declarations (i.e. the names of fields or local variables).

    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
     de
    -1.41
     inappropriés
    -1.35
     similar
    -1.32
    hlás
    -1.27
     jakieś
    -1.27
     Musiker
    -1.25
     no
    -1.22
    潆
    -1.22
     novin
    -1.21
     zatem
    -1.20
    POSITIVE LOGITS
    ━━
    1.37
     chapeau
    1.35
     explications
    1.33
     tirs
    1.32
     chaises
    1.30
    和
    1.30
    在
    1.28
     perle
    1.27
     レスト
    1.27
     chemise
    1.27
    Activations Density 0.014%

    No Known Activations