© 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. 31-GEMMASCOPE-2-RES-65K
    7. 10104
    Prev
    Next
    INDEX
    Explanations

    extracting and measuring data

    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_31_width_65k_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
    اب
    0.50
     wept
    0.46
    وی
    0.45
    ная
    0.44
    وى
    0.43
    ان
    0.42
     थाना
    0.42
    ೫
    0.41
     handwritten
    0.40
    at
    0.40
    POSITIVE LOGITS
     ይመ
    0.52
    gäng
    0.49
     Пі
    0.48
     উপভোগ
    0.48
     強
    0.48
     அம்ச
    0.48
    lll
    0.47
     obsah
    0.47
     Touchable
    0.47
     способны
    0.46
    Activations Density 0.020%

    No Known Activations