© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 833
    Prev
    Next
    INDEX
    Explanations

    Turn conversations into platinum results

    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_65k_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
    {
    0.55
     of
    0.54
    '
    0.54
    <0x80>
    0.52
    t
    0.48
    <0xA0>
    0.47
     a
    0.45
    (
    0.45
    -
    0.45
     (
    0.45
    POSITIVE LOGITS
    The
    0.47
    و
    0.47
    and
    0.46
    ко
    0.45
    IS
    0.45
    га
    0.44
    도
    0.42
    جراء
    0.41
    碐
    0.41
    هي
    0.41
    Activations Density 0.140%

    No Known Activations