© 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. 14489
    Prev
    Next
    INDEX
    Explanations

    Robert Jackson Lewis

    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
    <unused647>
    1.09
    lebr
    1.05
    oms
    1.05
    <unused2105>
    1.05
    <unused653>
    1.04
    絖
    1.02
    <unused644>
    1.01
    rame
    1.01
     qRT
    1.00
    <unused343>
    1.00
    POSITIVE LOGITS
    Thinking
    0.82
    sächlich
    0.80
    adhi
    0.79
     характеристики
    0.76
    ்ட்
    0.75
     Thinking
    0.75
    atively
    0.75
     я
    0.74
    тель
    0.73
     pensando
    0.73
    Activations Density 0.000%

    No Known Activations