© 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. 7880
    Prev
    Next
    INDEX
    Explanations

    Title or Rating

    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
    o
    1.67
    ۰
    1.51
    i
    1.46
    ing
    1.36
    u
    1.36
    a
    1.33
    र
    1.31
    y
    1.30
    zerel
    1.28
    erina
    1.28
    POSITIVE LOGITS
     Palabra
    1.68
     Solid
    1.66
     Με
    1.57
     전통
    1.56
     Những
    1.53
     solide
    1.53
     Cách
    1.52
    ົວ
    1.52
     目
    1.52
     Bots
    1.51
    Activations Density 0.002%

    No Known Activations