© 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. 4354
    Prev
    Next
    INDEX
    Explanations

    connector Flush Scrub explanation

    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
    s
    0.82
    on
    0.75
    org
    0.74
    gest
    0.73
    ga
    0.68
    son
    0.68
    era
    0.68
    Ly
    0.68
    wy
    0.67
    ling
    0.67
    POSITIVE LOGITS
    <unused969>
    1.29
    <unused2136>
    1.27
    <unused303>
    1.21
    <unused2112>
    1.21
    <unused2176>
    1.19
     sympathize
    1.18
     glPushMatrix
    1.18
     "$"
    1.17
    <unused349>
    1.17
    <unused127>
    1.16
    Activations Density 0.000%

    No Known Activations