© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7747
    Prev
    Next
    INDEX
    Explanations

    C++ standard library

    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_22_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
    ὥ
    1.06
    ὧ
    1.00
     पू
    0.95
     құ
    0.87
     ημέ
    0.87
     अलग
    0.84
     үчүн
    0.82
     вру
    0.82
     своего
    0.82
     времена
    0.80
    POSITIVE LOGITS
    rends
    0.83
    rof
    0.82
     quoique
    0.79
     Yards
    0.78
    ofed
    0.77
     studios
    0.77
     breathed
    0.77
     Studios
    0.76
    ̼
    0.76
     hev
    0.76
    Activations Density 0.005%

    No Known Activations