Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 441
    Prev
    Next
    INDEX
    Explanations

    as you know

    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
     as
    -1.60
     would
    -1.41
     D
    -1.30
     four
    -1.26
     showed
    -1.25
     demonstrates
    -1.23
     will
    -1.20
     if
    -1.20
     seven
    -1.16
     showing
    -1.16
    POSITIVE LOGITS
    龇
    1.47
    鶫
    1.45
     bardak
    1.39
     inconvénients
    1.32
    を活用
    1.31
     délais
    1.28
    basically
    1.26
     lentamente
    1.23
     bienven
    1.23
     coûts
    1.20
    Activations Density 0.128%

    No Known Activations