© 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. 108890
    Prev
    Next
    INDEX
    Explanations

    Irish names

    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
    ото
    -0.84
    ϵ
    -0.76
    >';
    -0.76
    Irish
    -0.75
    ワイン
    -0.75
     满
    -0.74
     plugged
    -0.73
     Belfast
    -0.72
     Irish
    -0.72
     Liberties
    -0.71
    POSITIVE LOGITS
    UNIVERS
    0.81
    ستانی
    0.79
     Respiration
    0.75
    toolStrip
    0.74
    恐れ
    0.74
    unshift
    0.73
     upang
    0.72
     hogyan
    0.71
     Erwart
    0.71
    Bier
    0.71
    Activations Density 0.024%

    No Known Activations