© 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. 5418
    Prev
    Next
    INDEX
    Explanations

    irritate, narrow, protect body parts

    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
    чительно
    0.57
    しろ
    0.57
     Field
    0.56
    いたら
    0.55
    >().
    0.55
     world
    0.54
    logram
    0.53
    たと
    0.53
     mund
    0.53
     July
    0.53
    POSITIVE LOGITS
     unsuspecting
    0.78
     Zellen
    0.76
     chromosomes
    0.74
     vulnerable
    0.73
     powierzchni
    0.72
     surrounding
    0.71
    缔
    0.70
     living
    0.70
     partenaires
    0.69
     सूर्या
    0.69
    Activations Density 0.142%

    No Known Activations