© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3624
    Prev
    Next
    INDEX
    Explanations

    writes, comments, quotes

    np_acts-logits-general · gemini-2.5-flash-lite

    lists; code blocks; markdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused2213>
    0.39
    <unused281>
    0.38
    <unused502>
    0.37
    လိုအပ်
    0.36
    <unused2177>
    0.35
    <unused700>
    0.35
     கூட்டணி
    0.35
    <unused540>
    0.34
    <unused2204>
    0.34
    <unused333>
    0.34
    POSITIVE LOGITS
     (
    0.53
     A
    0.46
     Mr
    0.45
    :[
    0.44
     ((
    0.44
     quoted
    0.44
     berjudul
    0.44
     from
    0.43
    :”
    0.42
     [
    0.42
    Activations Density 0.160%

    No Known Activations