© 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. 37609
    Prev
    Next
    INDEX
    Explanations

    name, models, text, looks, equipment, size

    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
    而不是
    0.46
    :
    0.45
     insofar
    0.42
     tandis
    0.41
     الحلقة
    0.40
     وكذلك
    0.39
    ،
    0.38
     yani
    0.38
    而非
    0.38
     മാത്രമേ
    0.38
    POSITIVE LOGITS
     elsewhere
    0.70
     ailleurs
    0.49
    での
    0.46
     eigene
    0.46
     eigenen
    0.44
     у
    0.42
    他の
    0.42
     ର
    0.42
     위한
    0.42
     Elsewhere
    0.42
    Activations Density 0.039%

    No Known Activations