© 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. 1115
    Prev
    Next
    INDEX
    Explanations

    license version or file metadata

    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
    ↺
    -0.71
     Belt
    -0.69
     Sober
    -0.68
    Ведь
    -0.67
     spars
    -0.66
     Championship
    -0.65
    kü
    -0.65
    ]?.
    -0.64
    aste
    -0.63
     ситуа
    -0.63
    POSITIVE LOGITS
     aérea
    0.76
    篑
    0.74
     پہ
    0.73
    osidad
    0.72
    nasium
    0.71
    uire
    0.70
    skog
    0.70
     שם
    0.69
    ordenadas
    0.69
    gráficos
    0.69
    Activations Density 0.067%

    No Known Activations