© 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. 149506
    Prev
    Next
    INDEX
    Explanations

    lift a finger

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

    simultaneously or context

    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
    toggle
    0.49
     可以
    0.45
     splice
    0.44
     χρήση
    0.44
    UG
    0.44
    仍
    0.43
     सल्
    0.43
    正则表达式
    0.43
     sólido
    0.42
     بش
    0.42
    POSITIVE LOGITS
    📬
    0.53
    Develop
    0.48
    Œ
    0.45
    神奈川
    0.45
     Dementia
    0.45
    🎥
    0.45
     Feminist
    0.45
    بلی
    0.44
    બાદ
    0.44
    Developing
    0.43
    Activations Density 0.001%

    No Known Activations