© 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. 12605
    Prev
    Next
    INDEX
    Explanations

    carnivore diet

    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
    (-
    1.15
    ("//
    1.06
    αιν
    1.03
     основания
    1.02
    年来
    1.01
     miserably
    1.00
    держи
    1.00
    aski
    0.99
    сли
    0.99
    /
    0.97
    POSITIVE LOGITS
     österreich
    1.44
    europa
    1.43
     Pompeo
    1.43
     riqueza
    1.42
    ยนตร์
    1.39
    >=</
    1.39
     Augustine
    1.38
     Vatican
    1.38
    ු
    1.37
    Abd
    1.36
    Activations Density 0.000%

    No Known Activations