© 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. 161646
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or warnings

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

    communication preferences

    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
    鐪
    0.48
    哞
    0.48
    袭击
    0.47
     bevest
    0.46
    delà
    0.45
     lí
    0.44
    relsen
    0.44
     सशक्त
    0.44
    市镇
    0.44
    给予
    0.44
    POSITIVE LOGITS
    ایط
    0.52
    з
    0.52
     ситуация
    0.48
    এবং
    0.47
    بی
    0.46
    ᒪ
    0.46
    クタ
    0.45
    모
    0.45
    ಮ
    0.45
    ENER
    0.44
    Activations Density 0.002%

    No Known Activations