© 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. 31-GEMMASCOPE-2-RES-262K
    7. 6904
    Prev
    Next
    INDEX
    Explanations

    difficulty, time, complexity, rating

    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_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
    牷
    0.36
    ন্যবাদ
    0.34
     შეგიძლიათ
    0.33
    飭
    0.32
     UserRepository
    0.31
     vattum
    0.31
    粮食
    0.31
    溸
    0.31
     chứ
    0.31
     Versicher
    0.31
    POSITIVE LOGITS
     range
    0.52
     approx
    0.49
     ≥
    0.46
     Approx
    0.46
     ≤
    0.45
    0.45
     approximately
    0.44
    5
    0.44
    Approx
    0.43
    範囲
    0.43
    Activations Density 0.171%

    No Known Activations