© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128330
    Prev
    Next
    INDEX
    Explanations

    html tags and structure

    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
     to
    -1.37
     for
    -1.07
     with
    -0.99
     ご
    -0.97
     çekilen
    -0.86
    adog
    -0.86
    لاحظ
    -0.86
    に
    -0.85
    ……。
    -0.85
     so
    -0.84
    POSITIVE LOGITS
    instead
    1.10
     fortsetter
    1.08
    Instead
    1.08
     trenger
    1.02
    リエステル
    1.01
     tilby
    0.99
     instead
    0.99
     byen
    0.98
    </b>
    0.95
    AGAIN
    0.93
    Activations Density 0.025%

    No Known Activations