© 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. 7379
    Prev
    Next
    INDEX
    Explanations

    light reflection and propagation

    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
     hydrazine
    1.14
    DataFrame
    0.98
     gauss
    0.97
    吡
    0.92
     actuators
    0.89
     pyautogui
    0.85
     calibrated
    0.84
     Gauss
    0.84
     glutathione
    0.84
    volatile
    0.84
    POSITIVE LOGITS
    媒
    1.19
     mediums
    1.12
    传播
    1.10
     TRAVEL
    1.09
     propagation
    1.08
     travel
    1.08
    travel
    1.08
     Snell
    1.07
     Propagation
    1.06
    Travel
    1.05
    Activations Density 0.080%

    No Known Activations