© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4379
    Prev
    Next
    INDEX
    Explanations

    forms and structured data

    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_16k_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
    يف
    0.48
     gleichen
    0.47
    الح
    0.40
     zwe
    0.39
    いう
    0.39
    也會
    0.39
     privilegi
    0.39
    並
    0.39
     แต
    0.39
     وت
    0.38
    POSITIVE LOGITS
     middle
    0.49
    purch
    0.48
    tin
    0.46
    tych
    0.46
    tenth
    0.46
    middle
    0.46
    ിച്ച്
    0.44
    smith
    0.44
    elective
    0.44
    tch
    0.44
    Activations Density 0.028%

    No Known Activations