© 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. 10-GEMMASCOPE-RES-131K
    7. 8359
    Prev
    Next
    INDEX
    Explanations

    commencing actions

    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_10/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
     he
    -2.28
    小声
    -2.13
     malfunction
    -2.09
    胳
    -2.08
    情報を
    -2.02
     reputed
    -1.95
    を変更
    -1.93
     occurrences
    -1.90
     overly
    -1.88
    OTHERS
    -1.88
    POSITIVE LOGITS
    1
    2.83
    n
    2.16
    3
    2.08
    4
    2.06
    s
    2.06
    2
    2.05
     But
    1.95
    م
    1.89
    西班牙
    1.88
    czne
    1.88
    Activations Density 0.040%

    No Known Activations