© 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. 885
    Prev
    Next
    INDEX
    Explanations

    code snippets and documentation

    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
    釹
    0.90
    EndZ
    0.88
    𒀊
    0.86
    >\<^
    0.86
    .)..
    0.84
    issantes
    0.84
    𒍪
    0.84
    irsi
    0.84
    heids
    0.84
    <unused89>
    0.84
    POSITIVE LOGITS
      
    0.82
     that
    0.65
     is
    0.64
     [
    0.63
     of
    0.62
     i
    0.61
     -
    0.60
     in
    0.60
    ,
    0.59
     the
    0.58
    Activations Density 0.031%

    No Known Activations