© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94403
    Prev
    Next
    INDEX
    Explanations

    you see

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

    phrases for clarification using "see"

    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
    Negative Logits
     sauv
    0.44
    发言
    0.42
    arne
    0.40
    砳
    0.40
    इनस
    0.40
    不错
    0.40
     hybridization
    0.40
    তম
    0.39
     monster
    0.39
    烽
    0.39
    POSITIVE LOGITS
     दरअसल
    0.57
     see
    0.57
    See
    0.55
    दरअसल
    0.54
    거든요
    0.54
    Because
    0.53
     See
    0.52
    because
    0.51
     because
    0.51
     BECAUSE
    0.50
    Activations Density 0.058%

    No Known Activations