© 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. 48923
    Prev
    Next
    INDEX
    Explanations

    types and categories

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

    types and categories

    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
    We
    0.41
    得意
    0.39
    我有
    0.38
    在上
    0.35
     เล่น
    0.35
     갖고
    0.35
     전에
    0.34
    眹
    0.34
    आई
    0.33
    ENCIA
    0.33
    POSITIVE LOGITS
     types
    0.41
    types
    0.39
     Ballon
    0.39
     forms
    0.38
     Response
    0.38
    halation
    0.38
     Balloon
    0.38
     trous
    0.37
     Types
    0.37
     loại
    0.37
    Activations Density 0.007%

    No Known Activations