© 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. 5504
    Prev
    Next
    INDEX
    Explanations

    tailored, requiring, descriptive, hate speech

    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
     नारायण
    0.66
     cookie
    0.64
     функциони
    0.63
    genomen
    0.62
     ಹೆ
    0.62
    prene
    0.61
    黄
    0.61
    差
    0.61
     쉬
    0.60
    תה
    0.60
    POSITIVE LOGITS
    uro
    0.68
     See
    0.63
    泽
    0.58
    שים
    0.57
     eryth
    0.56
    zv
    0.55
    ষেধ
    0.55
    rib
    0.54
    See
    0.54
     Picard
    0.54
    Activations Density 0.120%

    No Known Activations