© 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. 64596
    Prev
    Next
    INDEX
    Explanations

    lists and conjunctions

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

    lists and dictionaries

    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
    碛
    0.40
    হাওয়া
    0.38
     Naf
    0.37
     eich
    0.37
     তাহ
    0.37
    灾
    0.37
    丈夫
    0.36
    άρ
    0.36
    ску
    0.35
     Eich
    0.35
    POSITIVE LOGITS
    zing
    0.39
     /{
    0.37
     &_
    0.37
    =_
    0.36
    forall
    0.36
    /[
    0.36
    楫
    0.35
    rvats
    0.35
    /_
    0.34
    割合
    0.34
    Activations Density 0.128%

    No Known Activations