© 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. 34815
    Prev
    Next
    INDEX
    Explanations

    numbers and states

    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
     ネックレス
    -0.86
    ícias
    -0.80
     Tübingen
    -0.75
    focusable
    -0.74
    原型
    -0.74
    CMake
    -0.73
    ndose
    -0.73
     ссыл
    -0.71
    /…
    -0.71
    <0xF3>
    -0.70
    POSITIVE LOGITS
     бел
    0.79
     Aurang
    0.71
     Newman
    0.70
     Bid
    0.70
     Hermes
    0.70
    兵庫
    0.69
    レトロ
    0.68
    stdc
    0.68
     bidder
    0.68
     Diablo
    0.67
    Activations Density 0.019%

    No Known Activations