© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48179
    Prev
    Next
    INDEX
    Explanations

    official documents and standards

    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
    コーデ
    -0.78
     пъ
    -0.73
    フォロー
    -0.71
    致します
    -0.70
     hub
    -0.70
     dio
    -0.69
    ленную
    -0.68
     преобразова
    -0.68
    diali
    -0.66
    不管是
    -0.66
    POSITIVE LOGITS
     Circular
    1.60
    Circular
    1.52
     Bulletin
    1.41
     bulletin
    1.40
     circular
    1.39
    Bulletin
    1.29
    circular
    1.25
     bulletins
    1.11
    memor
    0.99
     Bullet
    0.99
    Activations Density 0.062%

    No Known Activations