© 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. 1015
    Prev
    Next
    INDEX
    Explanations

    database column names

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

    variable names and identifiers in programming code, particularly those containing underscores or representing database column names and object properties.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     his
    -2.22
     with
    -1.80
     where
    -1.77
     what
    -1.74
     our
    -1.72
     who
    -1.63
     whose
    -1.59
     didn
    -1.54
     and
    -1.47
     wasn
    -1.47
    POSITIVE LOGITS
    Lokasi
    1.43
     -
    1.37
     montant
    1.28
    8
    1.27
     doigt
    1.26
    Estructura
    1.20
    Pendidikan
    1.20
    的问道
    1.20
    Awal
    1.19
    Soporte
    1.18
    Activations Density 0.031%

    No Known Activations