© 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. 22-GEMMASCOPE-RES-131K
    7. 14728
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Perhaps
    -1.94
    What
    -1.89
    Despite
    -1.85
    Without
    -1.75
    Because
    -1.67
    Maybe
    -1.66
    That
    -1.66
    One
    -1.66
    恐れ
    -1.65
    Unlike
    -1.63
    POSITIVE LOGITS
    ar
    1.89
    C
    1.83
    J
    1.73
    B
    1.73
    H
    1.69
    N
    1.68
    .
    1.59
    P
    1.58
     technisch
    1.56
    Hmmm
    1.49
    Activations Density 0.000%

    No Known Activations