© 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. 50256
    Prev
    Next
    INDEX
    Explanations

    business and operations

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

    operating system specifications

    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
     أبي
    0.45
    Wy
    0.45
    鬢
    0.44
    微软雅黑
    0.42
    الية
    0.41
    navigator
    0.41
    toolkit
    0.41
    toolbox
    0.41
     घोषणा
    0.41
    晞
    0.40
    POSITIVE LOGITS
     хорошие
    0.53
     ì
    0.50
    }|\
    0.49
     Ã
    0.49
     TA
    0.47
     í
    0.47
     ï
    0.47
     ð
    0.47
     IPO
    0.46
     이게
    0.46
    Activations Density 0.001%

    No Known Activations