© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3118
    Prev
    Next
    INDEX
    Explanations

    GPL license declarations

    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
    Το
    -0.85
    గ
    -0.79
    CTE
    -0.75
    阿
    -0.75
    Bei
    -0.73
    Ն
    -0.73
    اگر
    -0.73
    Genesis
    -0.72
     Endocrinol
    -0.72
    CHD
    -0.71
    POSITIVE LOGITS
    ान्त
    0.75
     Persön
    0.75
    たぶん
    0.71
     afflicted
    0.69
     sic
    0.68
     ngừng
    0.67
    手中
    0.67
    oche
    0.67
    に対応
    0.66
     acquies
    0.66
    Activations Density 0.444%

    No Known Activations