© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 116776
    Prev
    Next
    INDEX
    Explanations

    choked on or back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ad
    0.61
    ap
    0.58
    ar
    0.57
    ab
    0.57
     apakah
    0.56
    A
    0.56
     includes
    0.55
    r
    0.55
     is
    0.55
    im
    0.54
    POSITIVE LOGITS
    들이
    0.62
    帳に追加
    0.62
     Chemists
    0.58
    中に
    0.58
     Aś
    0.55
    ７
    0.55
     亀
    0.55
    ２
    0.55
    نی
    0.54
     ಪ್ರಾರಂಭ
    0.54
    Activations Density 0.001%

    No Known Activations