© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15870
    Prev
    Next
    INDEX
    Explanations

    error detection and choice selection

    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
    Negative Logits
    <unused1049>
    1.13
    <unused2152>
    1.00
    <unused1815>
    0.99
    <unused317>
    0.99
    <unused2026>
    0.98
     callSettings
    0.98
     ObjData
    0.97
    <unused2182>
    0.95
    <unused1691>
    0.95
    <unused849>
    0.95
    POSITIVE LOGITS
     The
    0.95
    0.92
     A
    0.84
     S
    0.81
    The
    0.78
     K
    0.73
    k
    0.72
    Others
    0.70
     Sa
    0.69
     k
    0.69
    Activations Density 0.043%

    No Known Activations