© 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. 103150
    Prev
    Next
    INDEX
    Explanations

    location and hours

    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
     proverbial
    -0.73
     kuan
    -0.73
    を持った
    -0.71
     easier
    -0.68
    graphql
    -0.67
    cyj
    -0.67
     kuu
    -0.67
     contrario
    -0.67
     ネイル
    -0.66
    xmlns
    -0.66
    POSITIVE LOGITS
    Google
    1.60
     Google
    1.51
     google
    1.29
    google
    1.23
     GOOGLE
    1.10
    GOOGLE
    0.93
     GMB
    0.93
    ✭✭
    0.90
     reseñas
    0.90
    谷歌
    0.84
    Activations Density 0.004%

    No Known Activations