© 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. 12103
    Prev
    Next
    INDEX
    Explanations

    personalized training, native to

    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
     braced
    1.26
    Maybe
    1.25
    weighted
    1.20
    "/
    1.13
    s
    1.13
    Packed
    1.11
    Bracketing
    1.11
    Hold
    1.10
    Bought
    1.10
    itized
    1.10
    POSITIVE LOGITS
    ուն
    1.12
    鋤
    1.09
     സര്‍
    1.04
    ovu
    1.03
     प्राण
    0.99
    isin
    0.97
    ровала
    0.97
    蠱
    0.97
    鬚
    0.97
     އި
    0.97
    Activations Density 0.000%

    No Known Activations