© 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. 10-GEMMASCOPE-RES-131K
    7. 40987
    Prev
    Next
    INDEX
    Explanations

    id or name values

    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
    “
    -2.22
     preventing
    -2.14
     before
    -2.06
    ⼼
    -2.02
    .
    -1.93
     multifaceted
    -1.92
     οποίο
    -1.89
     rigorous
    -1.87
     striving
    -1.87
     provide
    -1.86
    POSITIVE LOGITS
    s
    2.08
     '
    1.95
     soooo
    1.86
     $-$
    1.85
     irres
    1.83
    ER
    1.83
     VERY
    1.81
    釙
    1.81
     AMAZING
    1.80
     Of
    1.80
    Activations Density 0.026%

    No Known Activations