© 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. 222889
    Prev
    Next
    INDEX
    Explanations

    definition , protection, reference, proudly, biggest, competitors

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

    explanation of choices

    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
    हम
    0.48
     MA
    0.46
    ाम
    0.45
    सीएस
    0.44
    मेल
    0.44
    PRA
    0.44
    ش
    0.44
    تمام
    0.43
    صح
    0.43
    میل
    0.43
    POSITIVE LOGITS
     casse
    0.46
     са
    0.46
     അരി
    0.46
     ውጤ
    0.46
     списка
    0.45
     제한
    0.45
     попы
    0.45
     코
    0.44
     edildi
    0.44
     réduite
    0.44
    Activations Density 0.000%

    No Known Activations