© 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. 6229
    Prev
    Next
    INDEX
    Explanations

    filename matches

    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
    amir
    0.79
     signé
    0.72
    ong
    0.71
    nos
    0.70
    ###############
    0.70
     pił
    0.66
     car
    0.65
     फ़र
    0.65
    roon
    0.64
     cha
    0.64
    POSITIVE LOGITS
    牢
    0.79
     conforming
    0.71
    solver
    0.70
     curricula
    0.70
    ㄇ
    0.70
    බ්
    0.68
    CONSTANT
    0.65
    खून
    0.65
    Conj
    0.65
     fatality
    0.64
    Activations Density 0.001%

    No Known Activations