© 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. 44929
    Prev
    Next
    INDEX
    Explanations

    quoted speech or dialogue

    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
    旲
    0.51
    AYLOR
    0.48
    មា
    0.48
    tais
    0.47
    ны
    0.47
    があります
    0.46
    дитесь
    0.45
     pentes
    0.45
    ডিট
    0.45
    нии
    0.44
    POSITIVE LOGITS
     And
    0.65
     Restaurant
    0.53
     But
    0.52
     That
    0.52
     Hard
    0.50
     “
    0.50
     Bacteria
    0.50
     Medicine
    0.50
     Quality
    0.50
     They
    0.49
    Activations Density 0.008%

    No Known Activations