© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8415
    Prev
    Next
    INDEX
    Explanations

    predicting categorical outcome or dependent variable

    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
    프트
    1.03
    zeczytaj
    0.97
    속
    0.96
    response
    0.95
    プト
    0.95
    طب
    0.93
    pea
    0.89
     속
    0.88
    thead
    0.88
    стива
    0.88
    POSITIVE LOGITS
    ee
    1.19
    iment
    1.17
    ational
    1.16
    iments
    1.13
    encing
    1.04
    ential
    1.03
    ial
    1.00
    iyordu
    0.99
     дел
    0.99
    evidence
    0.97
    Activations Density 0.060%

    No Known Activations