© 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. 8521
    Prev
    Next
    INDEX
    Explanations

    is crucial for documentation

    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
     Harb
    1.00
     Harp
    0.93
     젊
    0.92
     फंड
    0.90
    mercial
    0.88
     gav
    0.87
     Fad
    0.86
    খী
    0.85
    帑
    0.84
     flavored
    0.83
    POSITIVE LOGITS
    groupby
    0.75
    |\
    0.72
    뺑
    0.71
    [['
    0.71
     চলুন
    0.70
    \\\
    0.70
     गौरी
    0.70
     /\
    0.69
    \
    0.69
    [["
    0.69
    Activations Density 0.020%

    No Known Activations