© 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. 27914
    Prev
    Next
    INDEX
    Explanations

    as ... for, part ... for, Fig ... in

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

    hybrid and ever

    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
    I
    0.55
    J
    0.54
    S
    0.52
    C
    0.51
    A
    0.49
    on
    0.48
    N
    0.48
    an
    0.48
    ;&
    0.48
    Sweet
    0.47
    POSITIVE LOGITS
     どれ
    0.54
     ممكن
    0.51
     ChIP
    0.50
    ിൽ
    0.49
     גדול
    0.48
     টা
    0.48
     ridge
    0.47
     اين
    0.47
     Acest
    0.47
     വാർത്ത
    0.47
    Activations Density 0.000%

    No Known Activations