© 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. 34-GEMMASCOPE-RES-131K
    4. 2490
    Prev
    Next
    INDEX
    Explanations

    code completion prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     acom
    -0.88
     coper
    -0.82
     cose
    -0.78
    though
    -0.78
     aval
    -0.77
     aber
    -0.77
     medo
    -0.76
     apartament
    -0.76
    jooq
    -0.76
    てる
    -0.75
    POSITIVE LOGITS
    -...
    1.05
    geth
    1.05
    ...>
    0.98
     esfuerzan
    0.96
     trei
    0.95
     sencillos
    0.94
    crea
    0.93
     tři
    0.93
     perfiles
    0.93
     elástico
    0.93
    Activations Density 0.160%

    No Known Activations