© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 8263
    Prev
    Next
    INDEX
    Explanations

    vital to, modern, stainless steel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    들어
    0.98
     অন্তত
    0.92
     дам
    0.91
     screen
    0.90
    意
    0.89
     dough
    0.85
     करीब
    0.85
     Aids
    0.82
     экране
    0.82
    囊
    0.82
    POSITIVE LOGITS
    am
    1.23
    ത്തിനെ
    1.08
    কো
    1.05
    >';
    1.05
     proton
    1.04
    데요
    1.02
    :</
    1.01
    kapet
    1.00
    ir
    1.00
    佐
    0.99
    Activations Density 0.000%

    No Known Activations