© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84962
    Prev
    Next
    INDEX
    Explanations

    code and structured data

    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
    Ț
    -0.73
    カプ
    -0.70
     Rooney
    -0.69
    FixedSize
    -0.68
    래스
    -0.67
    gı
    -0.67
     הספר
    -0.66
     Gour
    -0.66
    imine
    -0.66
     TNA
    -0.65
    POSITIVE LOGITS
     calyx
    0.75
     ダブル
    0.72
     tramont
    0.67
    inspiring
    0.65
    mochila
    0.65
    ffeine
    0.65
    恭敬
    0.64
    himura
    0.64
     постоян
    0.63
    blogspot
    0.63
    Activations Density 0.072%

    No Known Activations