© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4201
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific terms

    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
     subsidy
    0.83
     incarnation
    0.78
     torsion
    0.78
     、,
    0.77
     expulsion
    0.76
     MDLVertex
    0.76
    𒅌
    0.76
    𒉰
    0.75
     ounce
    0.75
     retraction
    0.75
    POSITIVE LOGITS
     за
    0.82
     во
    0.73
     مؤ
    0.72
     من
    0.68
     الض
    0.66
    らす
    0.64
    是被
    0.63
    差
    0.63
     Fig
    0.63
     от
    0.62
    Activations Density 0.001%

    No Known Activations