© 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. 16-GEMMASCOPE-2-RES-262K
    7. 18113
    Prev
    Next
    INDEX
    Explanations

    pysanky, drift, artist, baker, toddler

    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_16_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
     is
    0.73
     was
    0.69
    是
    0.63
    は
    0.61
     OF
    0.61
     be
    0.60
    ↵↵
    0.58
     müssen
    0.58
     the
    0.57
    0.57
    POSITIVE LOGITS
    чи
    0.63
    ও
    0.59
    도
    0.58
    ही
    0.58
     особи
    0.57
    ہ
    0.54
    も含
    0.51
     პირადი
    0.50
    }^{-}\
    0.49
     फैक्ट
    0.49
    Activations Density 0.000%

    No Known Activations