© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1281
    Prev
    Next
    INDEX
    Explanations

    technical code and configuration

    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
     TAG
    -0.77
     sunt
    -0.76
    returnType
    -0.71
     negativ
    -0.71
     tage
    -0.71
    abre
    -0.71
    **********/
    -0.71
    Britannique
    -0.70
    tigte
    -0.70
    advantage
    -0.69
    POSITIVE LOGITS
    Arg
    0.66
     學
    0.65
     використо
    0.62
     razón
    0.62
    Flag
    0.61
     Drž
    0.61
    ชอบ
    0.61
    ファッション
    0.61
    Bolt
    0.60
    indak
    0.60
    Activations Density 0.051%

    No Known Activations