© 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. 165536
    Prev
    Next
    INDEX
    Explanations

    add in the next step

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

    acknowledging harmful terms

    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
    ;&#
    0.51
    ;"+
    0.48
    Cancelar
    0.46
    صاب
    0.43
     prostit
    0.43
    ცია
    0.43
    ادرات
    0.42
    ;",
    0.42
    !*\
    0.42
    Tecla
    0.41
    POSITIVE LOGITS
    iamo
    0.55
     ಆಹಾರ
    0.45
     FILL
    0.45
     एम
    0.45
     LINK
    0.44
     BOX
    0.43
    𝐳
    0.43
    asic
    0.43
     কেন্দ্রে
    0.43
     арт
    0.42
    Activations Density 0.000%

    No Known Activations