© 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. 89796
    Prev
    Next
    INDEX
    Explanations

    Shop now calls to action

    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
    g
    0.82
    in
    0.68
     a
    0.66
    в
    0.64
    ATED
    0.64
    j
    0.64
    ي
    0.64
    ва
    0.63
    لي
    0.62
    تين
    0.57
    POSITIVE LOGITS
    šit
    0.66
    س
    0.61
     jeho
    0.60
     senyawa
    0.60
     kriy
    0.59
    prar
    0.59
     for
    0.58
    सेप्ट
    0.58
     ব্যক্তি
    0.58
     بسیاری
    0.57
    Activations Density 0.002%

    No Known Activations