© 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. 22-GEMMASCOPE-RES-131K
    7. 25563
    Prev
    Next
    INDEX
    Explanations

    object mapping or copying

    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
    復帰
    -1.03
    lain
    -1.02
    ,
    -1.00
    -
    -0.98
    ✊
    -0.97
     Pendant
    -0.97
     on
    -0.96
     绘画
    -0.93
    DialogInterface
    -0.91
     Adventures
    -0.90
    POSITIVE LOGITS
     between
    1.30
     между
    1.23
     êtres
    1.12
     reposer
    1.11
    issens
    1.05
     kleinen
    1.05
    BURGH
    1.05
     превра
    1.03
    tamente
    1.01
     بيها
    1.01
    Activations Density 0.002%

    No Known Activations