© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 38736
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions and ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_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
    ()/
    0.41
    限于
    0.40
    /}{
    0.38
    ²/
    0.38
    اتها
    0.38
    പാട്
    0.38
    ／
    0.38
    িয়ে
    0.37
     подряд
    0.36
    (/[
    0.36
    POSITIVE LOGITS
    ths
    0.46
     *
    0.41
     poke
    0.41
    xido
    0.39
     chance
    0.38
     ratio
    0.38
     HP
    0.37
     Odds
    0.37
     Century
    0.37
    rds
    0.36
    Activations Density 0.033%

    No Known Activations