© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170336
    Prev
    Next
    INDEX
    Explanations

    accept our apologies

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

    with audits, reaction, standards, comfort

    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
    ات
    0.48
    ㄨ
    0.46
     metallurgy
    0.45
    ا
    0.45
    یده
    0.44
    ामुळे
    0.44
     usages
    0.43
     प्रतिमा
    0.42
    学
    0.42
    чни
    0.42
    POSITIVE LOGITS
    seat
    0.47
    ule
    0.47
     roku
    0.46
    msup
    0.45
    }}$.
    0.45
     rendez
    0.45
    lijk
    0.44
    vek
    0.44
    ]=\
    0.43
     samaj
    0.43
    Activations Density 0.001%

    No Known Activations