© 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. 4251
    Prev
    Next
    INDEX
    Explanations

    code or rules

    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
     phấn
    1.02
    pens
    0.97
    pani
    0.95
    抻
    0.95
    thus
    0.95
     tallest
    0.94
    抬头
    0.94
    vari
    0.93
    lands
    0.93
    ̃
    0.93
    POSITIVE LOGITS
    ;*/
    1.02
    弁
    1.01
    ;-
    1.01
    ;"
    1.00
    Assemble
    0.99
     desf
    0.98
     процес
    0.97
    cucumber
    0.97
    *;
    0.97
     ech
    0.96
    Activations Density 0.000%

    No Known Activations