© 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. 90287
    Prev
    Next
    INDEX
    Explanations

    copyright symbol

    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
    ADVANCED
    -0.75
    áč
    -0.74
    vä
    -0.73
     touchdowns
    -0.71
    avana
    -0.70
    Patrol
    -0.70
     btc
    -0.68
     watcher
    -0.68
     caravans
    -0.68
     Validator
    -0.66
    POSITIVE LOGITS
    总理
    0.76
    🦷
    0.72
     atún
    0.71
     wide
    0.70
     във
    0.69
     soziale
    0.68
     saumon
    0.68
     office
    0.67
    rils
    0.67
     Yee
    0.66
    Activations Density 0.046%

    No Known Activations