© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71788
    Prev
    Next
    INDEX
    Explanations

    UNITED STATES COURT OF APPEALS

    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
     همچنین
    -1.16
    ឋ
    -1.16
    kurang
    -1.13
    같이
    -1.13
     tanken
    -1.12
     grafik
    -1.11
     hacían
    -1.11
     hunde
    -1.11
     kuns
    -1.11
     vulgaires
    -1.10
    POSITIVE LOGITS
     and
    1.61
     on
    1.16
    /
    1.11
    ’
    1.07
    '
    1.05
    ,
    1.03
    orted
    1.02
    ‘
    1.02
     gull
    0.97
    en
    0.96
    Activations Density 0.549%

    No Known Activations