© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7279
    Prev
    Next
    INDEX
    Explanations

    identifying categories then elaborating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     bądź
    0.61
     [.
    0.60
    ([
    0.60
    $[\
    0.59
     ([
    0.59
    <unused479>
    0.58
    ['
    0.58
    [_
    0.57
    #[
    0.57
    getNumberOf
    0.56
    POSITIVE LOGITS
     quam
    0.81
     witch
    0.76
    টারে
    0.73
     such
    0.72
     sexuality
    0.70
     concurrency
    0.70
     suche
    0.69
    uch
    0.69
     residues
    0.68
     conundrum
    0.68
    Activations Density 0.186%

    No Known Activations