© 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. 217261
    Prev
    Next
    INDEX
    Explanations

    them than, stain forms, we furthermore

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

    silent watch

    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
    ോ
    0.51
    िल
    0.48
    nière
    0.47
     Endgame
    0.47
    ர
    0.47
    วน
    0.46
     소개해
    0.46
    у
    0.46
     Toxic
    0.45
    س
    0.44
    POSITIVE LOGITS
    .%
    0.54
    pm
    0.50
    .$$
    0.47
     দার্শন
    0.47
    ,"
    0.46
    curly
    0.46
     adversely
    0.45
    :.
    0.45
     ちゃん
    0.44
     thận
    0.44
    Activations Density 0.000%

    No Known Activations