© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56761
    Prev
    Next
    INDEX
    Explanations

    social media informal language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     genders
    0.48
     مصنوع
    0.45
     polinom
    0.43
     mascara
    0.43
     الملابس
    0.42
     країн
    0.42
    嗆
    0.41
     jezik
    0.40
     مختلف
    0.40
     Más
    0.40
    POSITIVE LOGITS
     следующие
    0.44
    occur
    0.44
     restructure
    0.44
    abase
    0.43
     influence
    0.43
     функции
    0.43
     VPT
    0.43
    员
    0.42
    Примеча
    0.42
    owaniu
    0.42
    Activations Density 0.010%

    No Known Activations