© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1427
    Prev
    Next
    INDEX
    Explanations

    SQL `*` tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     semicon
    0.81
     അധ
    0.76
    Jewish
    0.75
     stretching
    0.74
     ▸
    0.73
     kinder
    0.70
    Jupiter
    0.70
    宣
    0.69
     Spitzer
    0.69
    .•
    0.68
    POSITIVE LOGITS
     varchar
    1.58
     VARCHAR
    1.54
     COLLATE
    1.51
     NULL
    1.50
    varchar
    1.47
    InnoDB
    1.47
     FOREIGN
    1.44
     CONSTRAINT
    1.43
    VARCHAR
    1.42
     DISTINCT
    1.39
    Activations Density 0.120%

    No Known Activations