© 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. 15808
    Prev
    Next
    INDEX
    Explanations

    meaning and philosophy

    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
    base
    1.19
    roveň
    1.15
    adham
    1.13
    ulg
    1.12
    ümer
    1.09
    【
    1.07
    licher
    1.07
     zuf
    1.07
    patan
    1.06
    kar
    1.06
    POSITIVE LOGITS
     காட்ச
    1.60
    ೦
    1.55
     pleasantly
    1.54
    clothing
    1.53
     intently
    1.52
     Continued
    1.52
    WeekDates
    1.51
     evenly
    1.48
    Clothing
    1.48
    Continued
    1.48
    Activations Density 0.002%

    No Known Activations