© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14834
    Prev
    Next
    INDEX
    Explanations

    press Enter

    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
    น่า
    1.87
    ting
    1.86
    了
    1.86
    nya
    1.75
    க்
    1.74
    ns
    1.74
    서
    1.73
    nd
    1.73
    ్య
    1.71
    sum
    1.59
    POSITIVE LOGITS
    iroz
    2.06
     بالنسب
    1.98
    েশনের
    1.81
    ította
    1.74
    প্ট
    1.72
    stuffs
    1.69
    üte
    1.61
    igkeiten
    1.61
    ሖ
    1.61
    ጻ
    1.59
    Activations Density 0.000%

    No Known Activations