© 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. 44900
    Prev
    Next
    INDEX
    Explanations

    proper nouns and dates

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

    safety instructions

    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
    年月日
    0.42
    рон
    0.39
     dét
    0.38
    乙
    0.38
    ْن
    0.37
     Они
    0.37
     Кири
    0.37
    olution
    0.37
     unul
    0.37
     tenacious
    0.36
    POSITIVE LOGITS
    플레이
    0.40
     faucets
    0.39
     undercover
    0.38
    éa
    0.38
     camping
    0.38
    helicopter
    0.38
    /~
    0.37
    fear
    0.36
     Sheraton
    0.36
    Bes
    0.36
    Activations Density 0.000%

    No Known Activations