© 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. 2610
    Prev
    Next
    INDEX
    Explanations

    automatic operations

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

    automatic execution

    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
     университет
    0.21
    鶉
    0.21
    糖尿
    0.21
     فلم
    0.21
     লিখিতে
    0.21
     христиан
    0.20
     ಮಹ
    0.20
     pensare
    0.20
    謾
    0.20
     গিয়াছেন
    0.19
    POSITIVE LOGITS
     automatically
    0.43
    自动
    0.35
     автоматически
    0.32
     automáticamente
    0.31
     automatiquement
    0.30
     metadata
    0.30
     parsed
    0.30
     자동으로
    0.30
     Automatically
    0.30
     automatisch
    0.29
    Activations Density 0.600%

    No Known Activations