© 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. 87456
    Prev
    Next
    INDEX
    Explanations

    But, grand, drawn, range, sang, manual, effect

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

    run by AI, not necessarily ruled; Hand vanished; key embedded

    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
     disciples
    0.51
    ète
    0.50
    andae
    0.49
    ὴ
    0.43
     Wynne
    0.43
    ป์
    0.43
    այ
    0.42
    デート
    0.42
    ài
    0.41
     Sydney
    0.41
    POSITIVE LOGITS
    LEV
    0.56
    glob
    0.51
     المختلف
    0.49
    TREE
    0.48
    昷
    0.48
    RestClient
    0.48
    IED
    0.47
     ülke
    0.46
    //"
    0.46
    Ğ
    0.45
    Activations Density 0.001%

    No Known Activations