© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 3079
    Prev
    Next
    INDEX
    Explanations

    explaining information or troubleshooting

    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
    ய்டா
    1.34
    localVarHTTP
    1.25
     شرطونو
    1.23
    avacako
    1.19
    <unused1683>
    1.19
    <unused1155>
    1.17
    𒀚
    1.17
    𒐴
    1.17
    𒑜
    1.17
    acchatiti
    1.17
    POSITIVE LOGITS
    on
    0.95
    కి
    0.87
    al
    0.79
    is
    0.79
    as
    0.77
    లు
    0.77
    es
    0.77
    os
    0.75
    h
    0.74
    стро
    0.73
    Activations Density 0.000%

    No Known Activations