© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 669
    Prev
    Next
    INDEX
    Explanations

    audio channel numbers and formats

    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
    t
    -1.49
    s
    -1.48
     that
    -1.44
     usadas
    -1.32
     there
    -1.32
    old
    -1.32
    any
    -1.31
     pueden
    -1.29
    in
    -1.27
     hecha
    -1.27
    POSITIVE LOGITS
    を搭載
    1.32
    摃
    1.28
    體驗
    1.28
     a
    1.27
    пах
    1.24
    芹
    1.21
    Xna
    1.20
    ном
    1.18
     verba
    1.16
     batterie
    1.16
    Activations Density 0.015%

    No Known Activations