© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13906
    Prev
    Next
    INDEX
    Explanations

    Origin, Tala, chain

    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_13_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
     garment
    1.67
     jackets
    1.65
     tropos
    1.65
     garments
    1.62
     Ecuador
    1.58
     jacket
    1.56
    帚
    1.53
     Century
    1.53
     MSD
    1.52
     covalently
    1.52
    POSITIVE LOGITS
    Sche
    1.33
    ttino
    1.33
    sche
    1.26
    гля
    1.26
    юн
    1.23
    schein
    1.23
    B
    1.23
    sky
    1.21
    >>(
    1.20
    activité
    1.19
    Activations Density 0.000%

    No Known Activations