© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 69917
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and labels

    np_acts-logits-general · gemini-2.5-flash-lite

    axis labels and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﹀
    0.50
    ությունը
    0.48
    嘌
    0.47
    𝗖
    0.46
     ಸ್ಥಳ
    0.46
    ीजन
    0.44
    Photograph
    0.44
    Photography
    0.44
    ங்கல்
    0.43
    ც
    0.43
    POSITIVE LOGITS
     labels
    0.54
     s
    0.53
     Language
    0.47
     س
    0.47
    labels
    0.46
     Matlab
    0.46
     lin
    0.45
     定义
    0.44
     gyd
    0.44
     Labels
    0.43
    Activations Density 0.000%

    No Known Activations