© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1259
    Prev
    Next
    INDEX
    Explanations

    digits followed by parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    کروچ
    0.30
    疠
    0.28
    Flicky
    0.28
    睐
    0.27
    尼亚克
    0.27
    केमॉन
    0.27
    箬
    0.26
    [,,"
    0.26
    stepToken
    0.26
    მასრულ
    0.26
    POSITIVE LOGITS
    0.44
    S
    0.34
    s
    0.34
    v
    0.34
    2
    0.34
    4
    0.33
    -
    0.33
    3
    0.33
    D
    0.32
    N
    0.32
    Activations Density 0.103%

    No Known Activations