© 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. 113464
    Prev
    Next
    INDEX
    Explanations

    law, labor, signal, highest, wonderful

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

    APIs, pair, focused on, beyond competing

    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
     當
    0.57
     plaie
    0.53
     产品
    0.52
    酺
    0.52
     不需要
    0.51
    Polling
    0.51
    ير
    0.50
    Databaze
    0.49
     χρόνια
    0.48
     προϊόν
    0.47
    POSITIVE LOGITS
    h
    0.55
    l
    0.54
    tg
    0.52
    dd
    0.51
    hq
    0.50
    dy
    0.50
    ing
    0.48
    dh
    0.48
     Tanto
    0.48
    cs
    0.47
    Activations Density 0.000%

    No Known Activations