© 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. 7034
    Prev
    Next
    INDEX
    Explanations

    svg width and height

    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
    юсь
    0.96
    ชัย
    0.94
    脩
    0.90
     xạ
    0.86
    ফাজ
    0.85
    Comp
    0.83
    rats
    0.82
     sebelum
    0.82
    액
    0.81
    ریح
    0.80
    POSITIVE LOGITS
    dé
    1.21
    Popover
    1.09
    ിയ
    1.08
     descargar
    1.07
    dim
    1.06
     FALSE
    1.05
     FULLER
    1.05
     carta
    1.05
    tamb
    1.04
     Leh
    1.04
    Activations Density 0.001%

    No Known Activations