© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7763
    Prev
    Next
    INDEX
    Explanations

    education and learning

    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
    vdd
    1.56
     Bình
    1.52
    ূনতম
    1.50
    стье
    1.45
    兕
    1.43
    <unused1154>
    1.43
    㶪
    1.41
    ড়যন্ত্র
    1.41
    <unused945>
    1.41
     lwd
    1.39
    POSITIVE LOGITS
    作った
    1.44
    めた
    1.24
     memory
    1.19
     dispositif
    1.18
     প্রণ
    1.18
    暇
    1.17
    ν
    1.17
    Charles
    1.16
     contractions
    1.16
     musée
    1.15
    Activations Density 0.000%

    No Known Activations