© 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. 56036
    Prev
    Next
    INDEX
    Explanations

    URL `w` index

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

    writing and saving

    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
    ന്ത്ര
    0.55
    চীনের
    0.51
    ちょうど
    0.49
     echocardi
    0.46
    夼
    0.46
    ⓵
    0.45
    ⓶
    0.45
    ⚉
    0.45
    糈
    0.44
     করেন
    0.44
    POSITIVE LOGITS
     Writing
    0.79
     writing
    0.77
    writing
    0.76
     writable
    0.72
     write
    0.70
    write
    0.69
     Write
    0.68
     WRITE
    0.67
    writes
    0.67
    Writing
    0.66
    Activations Density 0.001%

    No Known Activations