© 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. 31504
    Prev
    Next
    INDEX
    Explanations

    this permission notice

    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
    Improvement
    -0.81
    pshot
    -0.81
     causas
    -0.81
     chá
    -0.76
    werden
    -0.75
    组
    -0.72
    組
    -0.71
     Ру
    -0.71
    umas
    -0.71
    solids
    -0.70
    POSITIVE LOGITS
    body
    0.68
    チャンネル
    0.68
    Decoration
    0.63
     Propriet
    0.63
    NX
    0.63
    widetilde
    0.63
    zaar
    0.62
    Dieser
    0.61
     gesche
    0.61
    жі
    0.60
    Activations Density 0.061%

    No Known Activations