© 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. 12448
    Prev
    Next
    INDEX
    Explanations

    physics and technical descriptions

    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
    Kc
    1.03
    GA
    1.02
    Lr
    0.95
    दों
    0.94
    jeh
    0.93
    Lm
    0.93
    ú
    0.92
    gx
    0.92
    ś
    0.92
    ème
    0.91
    POSITIVE LOGITS
     하면서
    1.24
    ʼn
    1.21
     Chưa
    1.20
     zebrafish
    1.18
    osaurs
    1.17
     핵
    1.12
     حساب
    1.12
     cannibal
    1.12
    ஞ்ஞான
    1.12
     yanında
    1.11
    Activations Density 0.001%

    No Known Activations