© 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. 33185
    Prev
    Next
    INDEX
    Explanations

    # or version

    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
     causal
    -0.80
     null
    -0.79
    list
    -0.79
    中の
    -0.75
     بسیار
    -0.75
     TC
    -0.73
     list
    -0.73
     solo
    -0.73
    quant
    -0.72
    LIST
    -0.70
    POSITIVE LOGITS
    Yeni
    0.68
    KOL
    0.68
    orti
    0.67
     Kongo
    0.66
     david
    0.66
     garland
    0.66
    יסטור
    0.66
     desenho
    0.66
    gameId
    0.66
    CUP
    0.65
    Activations Density 0.064%

    No Known Activations