© 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. 50466
    Prev
    Next
    INDEX
    Explanations

    easier than

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

    rules, requirements, consequences

    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
    ্ম্ম
    0.49
    矯
    0.48
    活動
    0.46
    ﯼ
    0.46
    rosi
    0.45
     workspace
    0.45
     digested
    0.44
     Jay
    0.44
     nanow
    0.44
    䟺
    0.44
    POSITIVE LOGITS
    maktadır
    0.48
     फाय
    0.48
    un
    0.48
    azem
    0.47
    l
    0.46
    stal
    0.46
    保证
    0.45
    r
    0.45
    isks
    0.45
    ul
    0.44
    Activations Density 0.000%

    No Known Activations