© 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. 15246
    Prev
    Next
    INDEX
    Explanations

    POST requests for data

    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
     regulars
    0.96
     matchup
    0.92
     matchups
    0.92
    𝗕
    0.86
     brisk
    0.86
     डीआर
    0.85
     Braz
    0.85
     bituminous
    0.84
     Grading
    0.83
     BBM
    0.83
    POSITIVE LOGITS
    ToRemove
    0.72
    Def
    0.69
    窃
    0.69
    Molecular
    0.69
     def
    0.68
     আবদুল্লাহ
    0.68
    世
    0.67
    ศี
    0.67
    resulting
    0.67
    му
    0.66
    Activations Density 0.002%

    No Known Activations