© 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. 11163
    Prev
    Next
    INDEX
    Explanations

    directory structures and comments

    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
     同じ
    1.33
     gd
    1.33
     másik
    1.30
    徃
    1.29
     mehrere
    1.25
     yanlış
    1.25
     Bukan
    1.24
     不是
    1.22
     இரண்டு
    1.20
     bukan
    1.20
    POSITIVE LOGITS
    -
    1.17
    !
    1.15
    ,
    1.09
    áž
    1.05
    ;
    1.03
    auks
    1.02
    .
    1.00
    worldly
    0.99
    ،
    0.97
    world
    0.95
    Activations Density 0.074%

    No Known Activations