© 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. 40510
    Prev
    Next
    INDEX
    Explanations

    list separators

    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
     of
    -1.99
     was
    -1.91
     this
    -1.81
    ):
    -1.77
     during
    -1.60
    écial
    -1.59
     increase
    -1.54
     it
    -1.52
     had
    -1.47
     by
    -1.43
    POSITIVE LOGITS
     a
    2.06
     mengumumkan
    1.78
     uſ
    1.73
    inspiring
    1.71
    creating
    1.67
     Accesorios
    1.65
     mengakui
    1.61
     jezt
    1.58
    lllllllll
    1.55
     malheure
    1.54
    Activations Density 0.384%

    No Known Activations