© 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. 67538
    Prev
    Next
    INDEX
    Explanations

    wrote:

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

    communications and statements

    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
    \@
    0.39
    写法
    0.38
     本
    0.37
     Properties
    0.37
    acja
    0.37
     Day
    0.36
     자동
    0.36
    nań
    0.36
     Writing
    0.35
     Ceramic
    0.35
    POSITIVE LOGITS
    ليب
    0.43
    dons
    0.40
    통령
    0.39
    नाले
    0.38
    崗
    0.38
     quantidades
    0.38
    ফিন
    0.37
     Kool
    0.37
    ﹉
    0.37
    dicts
    0.37
    Activations Density 0.001%

    No Known Activations