© 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. 7767
    Prev
    Next
    INDEX
    Explanations

    wikipedia links

    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
    नाने
    0.90
    व्यवस्था
    0.89
     rozmi
    0.85
    Akh
    0.84
    (
    0.83
    require
    0.83
    कम
    0.83
     Akh
    0.82
     કર્યો
    0.81
     quá
    0.81
    POSITIVE LOGITS
    <unused494>
    0.95
     stardom
    0.93
     prosperity
    0.92
     remission
    0.91
     munch
    0.88
     spell
    0.86
     phúc
    0.82
     impl
    0.82
     মুশ
    0.82
     part
    0.81
    Activations Density 0.035%

    No Known Activations