© 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. 7687
    Prev
    Next
    INDEX
    Explanations

    Nebraska and associated terms

    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
    '
    -3.39
     edged
    -2.22
    umbledore
    -2.14
    henswürdigkeiten
    -2.03
     животные
    -2.02
    찮
    -1.98
     Bioaccumulative
    -1.98
    stationary
    -1.98
    砚
    -1.96
    weeney
    -1.90
    POSITIVE LOGITS
    6
    2.94
    5
    2.80
    3
    2.75
    8
    2.61
     chas
    2.55
    ными
    2.44
    k
    2.42
    ྵ
    2.42
     unmistak
    2.41
    0
    2.38
    Activations Density 0.003%

    No Known Activations