© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12445
    Prev
    Next
    INDEX
    Explanations

    code snippets and punctuation

    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_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
     first
    -1.08
     If
    -1.07
     you
    -1.03
     commonly
    -1.03
     required
    -0.99
     What
    -0.96
     The
    -0.94
     It
    -0.93
    atifs
    -0.93
     providing
    -0.93
    POSITIVE LOGITS
     panier
    1.09
     verbe
    1.04
     bì
    1.03
     jeter
    1.02
    всегда
    1.01
    yea
    0.99
     escalier
    0.99
     formules
    0.98
     صفحۀ
    0.97
     dessins
    0.97
    Activations Density 0.015%

    No Known Activations