© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11739
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    uss
    2.49
    iba
    2.28
    .
    2.27
    द्धांत
    2.25
    utie
    2.20
    hi
    2.19
     cillum
    2.19
    inu
    2.19
    ap
    2.15
    ord
    2.15
    POSITIVE LOGITS
    ಾಮ
    2.86
     Caja
    2.69
     Información
    2.63
    UTF
    2.61
     italics
    2.58
     سلس
    2.57
     半袖
    2.54
    垩
    2.54
     fumes
    2.53
     válv
    2.49
    Activations Density 0.002%

    No Known Activations