© 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. 10475
    Prev
    Next
    INDEX
    Explanations

    similar to

    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
    นด์
    2.74
    ی
    2.73
    囪
    2.53
    low
    2.47
    নিক
    2.44
    ki
    2.37
    riez
    2.35
    kans
    2.28
    shi
    2.27
    ই
    2.19
    POSITIVE LOGITS
    icelli
    2.89
    affold
    2.81
    場合に
    2.77
    ์
    2.76
     bearing
    2.75
    千萬
    2.71
    Especific
    2.71
    dyl
    2.67
    टेज
    2.66
    ेक्स
    2.64
    Activations Density 0.034%

    No Known Activations