© 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. 5067
    Prev
    Next
    INDEX
    Explanations

    you saved, so far

    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
    ल्स
    0.65
    носи
    0.62
     prénom
    0.60
     be
    0.60
     pr
    0.59
    ואה
    0.57
     одна
    0.56
    ϛ
    0.55
    urers
    0.55
     ကို
    0.55
    POSITIVE LOGITS
     বিএন
    0.75
     ጉዳ
    0.71
    र्में
    0.70
    ोटेन
    0.69
    ColumnKind
    0.69
     短
    0.69
    短
    0.68
     audioElement
    0.67
    ifar
    0.67
     agribusiness
    0.66
    Activations Density 0.041%

    No Known Activations