© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12189
    Prev
    Next
    INDEX
    Explanations

    `byte`, `local`, `com`, `White`, `Alias`, ` NULL`, `related`

    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_22/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
     概要
    -1.09
    ्यों
    -1.02
    已經
    -1.00
    IVIDUAL
    -0.97
    였다
    -0.96
    ：……
    -0.96
     mittlerweile
    -0.95
    もうすぐ
    -0.92
     inzwischen
    -0.92
    ߞ
    -0.90
    POSITIVE LOGITS
    称为
    1.07
    फ
    0.91
    श
    0.89
     as
    0.88
     at
    0.85
     on
    0.84
     åt
    0.82
    เป็น
    0.79
     not
    0.78
     called
    0.77
    Activations Density 0.010%

    No Known Activations