© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3840
    Prev
    Next
    INDEX
    Explanations

    Option 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2.81
    2.70
    2.68
    2.61
    ʚ
    2.51
    tan
    2.48
    2.46
    thest
    2.44
    )+'
    2.43
    ヂストン
    2.41
    POSITIVE LOGITS
    ோ
    2.97
     ouv
    2.95
    깐
    2.92
     оце
    2.81
    waitUntil
    2.67
    DrawerToggle
    2.57
     sapp
    2.57
    ம்
    2.56
    గ
    2.56
     prend
    2.53
    Activations Density 0.098%

    No Known Activations