© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5038
    Prev
    Next
    INDEX
    Explanations

    to tailor

    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_17_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
    telling
    0.77
    ten
    0.75
    teller
    0.74
     thinker
    0.74
     rivalry
    0.73
    gladbach
    0.72
     wist
    0.71
    ư
    0.70
    تب
    0.69
    loride
    0.69
    POSITIVE LOGITS
     compétences
    0.86
     जिला
    0.86
     jednost
    0.86
     migliori
    0.86
     các
    0.82
    ޞ
    0.80
     چیر
    0.78
     изу
    0.77
     incompet
    0.77
     อิน
    0.76
    Activations Density 0.019%

    No Known Activations