© 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. 6940
    Prev
    Next
    INDEX
    Explanations

    laws and practices

    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
    نو
    1.10
    Cli
    1.03
    スカート
    1.03
     Parker
    1.02
     গাড়ি
    1.02
     Sprach
    1.01
    Capp
    1.01
    ﷺ
    1.00
    Nash
    1.00
    cursos
    1.00
    POSITIVE LOGITS
    icore
    0.89
    engineer
    0.87
    dims
    0.86
     engineered
    0.86
     accumulates
    0.84
    േ
    0.84
     مين
    0.83
    poss
    0.81
     wonders
    0.81
     effic
    0.80
    Activations Density 0.000%

    No Known Activations