© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12628
    Prev
    Next
    INDEX
    Explanations

    spontaneously, automatically, or by discovery

    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_16k_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
     berse
    1.06
     HEIGHT
    1.03
    孪
    0.99
     пора
    0.97
     highlight
    0.95
    GAIN
    0.93
    DE
    0.93
    ᅦ
    0.92
     bane
    0.91
    istaa
    0.91
    POSITIVE LOGITS
     haphazard
    1.72
     improvis
    1.64
     spont
    1.56
     improvisation
    1.55
    随意
    1.54
     impromptu
    1.54
     random
    1.50
     espont
    1.50
     spontaneously
    1.49
     Impro
    1.48
    Activations Density 0.611%

    No Known Activations