© 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. 8051
    Prev
    Next
    INDEX
    Explanations

    setting names and titles

    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
     dieting
    1.00
     outta
    0.93
    LevelLinking
    0.90
    NP
    0.85
     NP
    0.84
    ㄈ
    0.83
    _{-\
    0.83
    듭
    0.82
     undone
    0.81
     SDP
    0.81
    POSITIVE LOGITS
    hist
    1.00
    tight
    1.00
    histoire
    0.89
    scatter
    0.88
    HIST
    0.87
     HIST
    0.87
    ax
    0.83
    imshow
    0.82
     hist
    0.82
    ophilus
    0.82
    Activations Density 0.019%

    No Known Activations