© 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. 6019
    Prev
    Next
    INDEX
    Explanations

    books and authors

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

    academic subjects and concepts

    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
    沉积
    0.38
    铳
    0.35
     gacche
    0.35
    乸
    0.35
    餚
    0.34
    器的
    0.34
    蹰
    0.34
    ูนย์
    0.34
    তাদের
    0.33
    ujete
    0.33
    POSITIVE LOGITS
     for
    0.58
    |
    0.55
     or
    0.53
     in
    0.52
     and
    0.49
     with
    0.49
     on
    0.47
    :
    0.47
     from
    0.45
     new
    0.44
    Activations Density 0.003%

    No Known Activations