© 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. 38942
    Prev
    Next
    INDEX
    Explanations

    coconut-related information

    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
    -3.11
    .”
    -2.94
    ed
    -2.86
     OF
    -2.66
    ING
    -2.59
    真的是
    -2.58
    0
    -2.52
    I
    -2.50
    y
    -2.31
    -2.31
    POSITIVE LOGITS
    ции
    2.84
    ୌ
    2.78
    
    2.70
    酲
    2.67
    莿
    2.66
    ﺢ
    2.58
    🛖
    2.44
    𓍊
    2.42
    昞
    2.42
    videobot
    2.38
    Activations Density 0.002%

    No Known Activations