© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5040
    Prev
    Next
    INDEX
    Explanations

    L words, Rel words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rho
    0.70
    阿
    0.68
     study
    0.68
    Stack
    0.66
     t
    0.66
    St
    0.65
     Stack
    0.64
    യെ
    0.63
    Alger
    0.63
     designed
    0.62
    POSITIVE LOGITS
    ⚊
    0.68
    ানন্দ
    0.64
    Vé
    0.62
     caval
    0.62
    actions
    0.61
    unehmen
    0.60
    ong
    0.60
    atching
    0.59
     بالا
    0.58
     kuts
    0.58
    Activations Density 0.078%

    No Known Activations