© 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. 32778
    Prev
    Next
    INDEX
    Explanations

    dates and place 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
    verlet
    -0.85
    マンド
    -0.83
    jau
    -0.81
    rencia
    -0.74
    rification
    -0.73
    licación
    -0.73
    opardy
    -0.72
    Raja
    -0.72
    Baron
    -0.72
     бактери
    -0.71
    POSITIVE LOGITS
    годні
    0.86
    Muslim
    0.70
     Louisville
    0.69
     isComment
    0.68
     Muslim
    0.68
    Portuguese
    0.68
     지역
    0.68
     Cambridge
    0.67
     Portuguese
    0.66
    VV
    0.66
    Activations Density 0.017%

    No Known Activations