© 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-262K
    7. 123964
    Prev
    Next
    INDEX
    Explanations

    comparing concepts like dark/light, yin/yang

    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
     enam
    0.50
    wide
    0.46
     Month
    0.46
     साल
    0.43
     छह
    0.43
    self
    0.40
    six
    0.39
     ६
    0.39
     langt
    0.39
    type
    0.39
    POSITIVE LOGITS
    務
    0.49
     частью
    0.46
    農業
    0.46
    規劃
    0.43
    ovania
    0.43
    考慮
    0.43
    傳
    0.42
     BAK
    0.42
     ጋ
    0.42
    тері
    0.42
    Activations Density 0.001%

    No Known Activations