© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2077
    Prev
    Next
    INDEX
    Explanations

    closing parentheses, braces, brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
     XNUMX
    1.09
     hum
    1.04
    ,
    1.00
     trad
    1.00
     diverting
    1.00
     ment
    0.99
     unending
    0.98
     crush
    0.97
     general
    0.96
     crude
    0.96
    POSITIVE LOGITS
    də
    1.42
    冭
    1.41
    isz
    1.40
    ForRule
    1.40
     கலோர
    1.39
    uyó
    1.38
    ꗗ
    1.35
    ()");
    1.35
    𒊍
    1.34
    <unused1411>
    1.34
    Activations Density 0.032%

    No Known Activations