© 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. 7511
    Prev
    Next
    INDEX
    Explanations

    drawing out or sliver

    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
    uously
    1.14
    ilot
    0.94
    PCT
    0.91
    uous
    0.91
    挡
    0.90
    ière
    0.89
    ilion
    0.89
    illons
    0.86
    urent
    0.86
    ilis
    0.85
    POSITIVE LOGITS
    例
    1.07
    estring
    1.03
    emaker
    0.96
    emaking
    0.95
    ใส่
    0.94
     darg
    0.94
    elace
    0.93
    ebox
    0.91
     dateFormat
    0.90
     enseign
    0.89
    Activations Density 0.023%

    No Known Activations