© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 30950
    Prev
    Next
    INDEX
    Explanations

    opods

    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_16_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
    ك
    0.67
    कश
    0.63
     दिन
    0.63
    amber
    0.60
    ambar
    0.60
     आने
    0.58
    alities
    0.58
    arni
    0.58
     های
    0.57
    aina
    0.57
    POSITIVE LOGITS
    <0x9F>
    0.66
    闾
    0.60
    é
    0.57
    ե
    0.55
     Г
    0.52
     fün
    0.52
     grammat
    0.52
    يئة
    0.52
     liberté
    0.52
    槸
    0.52
    Activations Density 0.001%

    No Known Activations