© 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. 34127
    Prev
    Next
    INDEX
    Explanations

    PCBs, Faulkner, biphenyls

    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
    ED
    1.16
    an
    1.03
    ם
    0.99
    \
    0.97
    R
    0.92
    ку
    0.91
    1
    0.91
    kw
    0.88
     with
    0.85
    ed
    0.84
    POSITIVE LOGITS
     ideales
    0.70
     espèces
    0.69
    و
    0.67
    的的
    0.67
    的支持
    0.64
     ಹೇಳಿದರು
    0.64
     покуп
    0.63
     авгу
    0.63
     مقدم
    0.62
     attrakt
    0.62
    Activations Density 0.001%

    No Known Activations