© 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. 165321
    Prev
    Next
    INDEX
    Explanations

    special humanitarian visa

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

    drakeposting meme preference

    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
     项目
    0.49
     wewnętr
    0.48
    ','$
    0.47
     siebie
    0.47
     Мін
    0.47
     determinación
    0.46
     hará
    0.45
    МІ
    0.45
     '$(
    0.45
     خطا
    0.45
    POSITIVE LOGITS
    單
    0.50
    TS
    0.49
    das
    0.48
     egyptian
    0.48
     japan
    0.47
    乳
    0.47
     europé
    0.46
     opposition
    0.46
    ਡ
    0.46
    n
    0.46
    Activations Density 0.000%

    No Known Activations