© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 20991
    Prev
    Next
    INDEX
    Explanations

    android util content app

    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
    이지만
    0.56
    ය
    0.48
    이가
    0.48
    കൾ
    0.47
     нарушения
    0.47
    ಟಕ
    0.47
    이어
    0.45
    วาม
    0.45
    cional
    0.45
    lation
    0.44
    POSITIVE LOGITS
    し
    0.59
     trigo
    0.55
     out
    0.55
     tuvo
    0.49
     equilib
    0.49
    SQLALCHEMY
    0.49
    מ
    0.49
     opér
    0.49
    ুর
    0.48
     pubblic
    0.48
    Activations Density 0.002%

    No Known Activations