© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7320
    Prev
    Next
    INDEX
    Explanations

    land and sound

    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_22_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
     Seitz
    0.99
     극
    0.92
    극
    0.91
    칠
    0.91
    гийн
    0.87
    घव
    0.87
     UIC
    0.86
    ঈ
    0.86
     Bee
    0.86
     Shee
    0.86
    POSITIVE LOGITS
    اند
    2.07
    AND
    1.98
    ants
    1.93
    нд
    1.87
    ANT
    1.85
    анд
    1.85
    ಂಡ
    1.83
    ANDA
    1.81
    ant
    1.78
    andy
    1.77
    Activations Density 0.743%

    No Known Activations