© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2838
    Prev
    Next
    INDEX
    Explanations

    under the license

    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
     menambahkan
    -0.71
     抗
    -0.67
     informacija
    -0.66
    THANK
    -0.65
     gezien
    -0.64
    covered
    -0.63
    insider
    -0.63
     inside
    -0.63
    richtungen
    -0.62
     esperienze
    -0.62
    POSITIVE LOGITS
    リーズ
    0.73
    acă
    0.70
     fortnight
    0.69
     ribos
    0.69
    OLOG
    0.69
     Gibbon
    0.68
    ataan
    0.68
    ჷ
    0.68
    コロ
    0.67
     divisible
    0.66
    Activations Density 0.085%

    No Known Activations