© 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. 100357
    Prev
    Next
    INDEX
    Explanations

    reason why

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

    list markdown and code formatting

    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
    โ
    0.50
     trakt
    0.48
    奖励
    0.46
     narr
    0.46
    ព័ន្ធ
    0.46
    ב
    0.46
     الأولى
    0.45
    最初は
    0.45
    Rewarded
    0.45
    หลังจาก
    0.45
    POSITIVE LOGITS
     Watertown
    0.48
     Utica
    0.47
     चें
    0.47
     Anaheim
    0.46
    }$=
    0.45
     Tukey
    0.44
     Peoria
    0.44
     same
    0.43
     Chem
    0.43
     Jacksonville
    0.42
    Activations Density 0.001%

    No Known Activations