© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198235
    Prev
    Next
    INDEX
    Explanations

    collectioncoach ifsafe collectiondiscover usefulanother oneAwesome Imagesseveral secrets

    np_acts-logits-general · gemini-2.5-flash-lite

    directions to image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ко
    0.53
    ግዳ
    0.48
    Ó
    0.47
    cen
    0.47
    kün
    0.47
    ka
    0.46
    ādi
    0.46
    का
    0.46
    lä
    0.46
    كان
    0.46
    POSITIVE LOGITS
    ሒ
    0.43
    テック
    0.43
     chronology
    0.42
    滚动
    0.42
     southernmost
    0.41
     stylu
    0.41
     tú
    0.41
     splurge
    0.41
     calendário
    0.40
     sitio
    0.40
    Activations Density 0.000%

    No Known Activations