© 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. 181769
    Prev
    Next
    INDEX
    Explanations

    introduce, redesigned, lack, free

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

    identify and list

    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
    そして
    0.59
     그리고
    0.56
     oscillation
    0.54
    ב
    0.52
     LPTMR
    0.52
    фр
    0.51
    그리고
    0.50
     oscillations
    0.49
     orbitals
    0.48
     т
    0.47
    POSITIVE LOGITS
    azada
    0.48
    ombies
    0.46
    人才
    0.46
    yahoo
    0.46
    缺乏
    0.45
    错误的
    0.45
    退休
    0.44
    Wrong
    0.44
    ளுடைய
    0.43
     выну
    0.43
    Activations Density 0.000%

    No Known Activations