© 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. 64390
    Prev
    Next
    INDEX
    Explanations

    cali, calib, kali, kaly variants

    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
    σίας
    -0.76
    Nivel
    -0.75
    闌
    -0.73
    💺
    -0.71
    дите
    -0.71
     suggestions
    -0.68
    Very
    -0.68
     even
    -0.68
    calcular
    -0.68
    矯
    -0.67
    POSITIVE LOGITS
    ≠
    0.87
     cali
    0.85
     amostra
    0.83
    вшиеся
    0.81
     Cali
    0.79
    ЛОВ
    0.76
    ㄲ
    0.74
     LAST
    0.73
    yog
    0.73
     dezembro
    0.73
    Activations Density 0.023%

    No Known Activations