© 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. 15966
    Prev
    Next
    INDEX
    Explanations

    melody: feel, ideas

    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
    <unused2170>
    1.43
    <unused943>
    1.42
    <unused620>
    1.41
    <unused752>
    1.40
    <unused1771>
    1.39
    <unused431>
    1.38
    <unused1643>
    1.38
    <unused802>
    1.37
    <unused1014>
    1.37
    <unused903>
    1.37
    POSITIVE LOGITS
    is
    0.79
    g
    0.76
    ing
    0.70
    y
    0.70
    in
    0.69
    th
    0.69
    os
    0.69
    min
    0.68
    down
    0.65
    ph
    0.65
    Activations Density 0.000%

    No Known Activations