© 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. 67635
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by brace or cell

    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
    potentially
    -1.52
     ʻ
    -1.41
    垆
    -1.39
    hopefully
    -1.38
     $-$
    -1.38
    なんだか
    -1.37
     –
    -1.36
     ingenu
    -1.35
     appelé
    -1.34
     Dinas
    -1.34
    POSITIVE LOGITS
     there
    2.13
     Eight
    1.77
     it
    1.67
     before
    1.63
     seven
    1.60
     this
    1.58
     any
    1.55
     Additional
    1.55
     one
    1.50
    หรือ
    1.50
    Activations Density 0.008%

    No Known Activations