© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5909
    Prev
    Next
    INDEX
    Explanations

    windows file paths and directory creation

    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_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <unused1366>
    1.12
    <unused1399>
    1.06
    <unused1522>
    1.05
    <unused1547>
    1.05
    <unused1314>
    1.03
    <unused1531>
    1.03
    một
    1.03
    <unused1600>
    1.03
    <unused1552>
    1.02
    𐰰
    1.02
    POSITIVE LOGITS
     se
    0.73
     form
    0.70
     set
    0.63
    able
    0.61
     total
    0.60
    house
    0.60
     pass
    0.58
     forms
    0.58
    en
    0.58
    점이
    0.57
    Activations Density 0.003%

    No Known Activations