© 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. 31-GEMMASCOPE-2-RES-262K
    7. 75603
    Prev
    Next
    INDEX
    Explanations

    introductions and descriptions

    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_31_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
     ไหร่
    0.55
    रहे
    0.54
    臧
    0.53
    мы
    0.53
    ней
    0.52
    ampu
    0.52
     всей
    0.52
    യ
    0.52
    人員
    0.51
    مكان
    0.48
    POSITIVE LOGITS
    o
    0.52
     FER
    0.45
     el
    0.43
     la
    0.42
     and
    0.41
     help
    0.41
     lou
    0.41
    SCH
    0.40
     isinstance
    0.40
    <0xAB>
    0.39
    Activations Density 0.000%

    No Known Activations