© 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. 7319
    Prev
    Next
    INDEX
    Explanations

    d words

    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
    лено
    0.86
    ño
    0.76
    usc
    0.75
    uable
    0.75
    ূন
    0.73
    ceptible
    0.73
    ப்படுகிறது
    0.73
    퇸
    0.72
    ಡುವುದ
    0.72
    ácia
    0.71
    POSITIVE LOGITS
    di
    1.05
    ెల
    1.03
    renti
    1.01
     di
    1.00
    eggi
    0.99
    ebi
    0.99
    ini
    0.97
     DI
    0.97
    istiche
    0.96
     della
    0.95
    Activations Density 0.053%

    No Known Activations