© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2479
    Prev
    Next
    INDEX
    Explanations

    please reach

    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
     Please
    0.77
    личие
    0.74
     pleads
    0.74
    Please
    0.74
    瑋
    0.73
     Crimes
    0.72
     Niles
    0.72
    spender
    0.70
     Snakes
    0.68
    chsler
    0.68
    POSITIVE LOGITS
     don
    0.74
     достига
    0.72
    reach
    0.67
    访问
    0.66
    ola
    0.65
    电
    0.63
     ikke
    0.63
     reach
    0.63
     aren
    0.63
    म
    0.63
    Activations Density 0.077%

    No Known Activations