© 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. 44813
    Prev
    Next
    INDEX
    Explanations

    surrender and relinquish

    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
    2
    -3.38
    y
    -2.95
    in
    -2.92
    as
    -2.84
    '
    -2.83
    猻
    -2.83
            
    -2.70
    3
    -2.67
    9
    -2.64
    玙
    -2.61
    POSITIVE LOGITS
    ⽩
    2.92
    媗
    2.59
     zullen
    2.42
     With
    2.38
     Moreover
    2.34
     ONLY
    2.31
    灕
    2.28
     Propiedad
    2.23
    嗵
    2.23
    呖
    2.19
    Activations Density 0.001%

    No Known Activations