© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 98841
    Prev
    Next
    INDEX
    Explanations

    or other choices

    np_acts-logits-general · gemini-2.5-flash-lite

    explicit sexual content and harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     हालात
    0.52
     Fiverr
    0.50
     hassles
    0.48
    ק
    0.46
    Ç
    0.46
    現實
    0.46
    Қ
    0.44
    機能
    0.43
    現実
    0.42
    เพราะ
    0.42
    POSITIVE LOGITS
     computeEncoder
    0.48
    存档备份
    0.44
     অথবা
    0.43
     abundances
    0.42
    fqsen
    0.41
     ataupun
    0.41
    
    0.41
     columnspan
    0.41
    طلق
    0.41
     occult
    0.41
    Activations Density 0.003%

    No Known Activations