© 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. 142615
    Prev
    Next
    INDEX
    Explanations

    url path segment /pub

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

    original code

    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
     кой
    0.49
    واج
    0.48
     দিলাম
    0.47
    你在
    0.46
     विभागा
    0.45
     itineraries
    0.45
    ాలే
    0.45
    하지만
    0.44
    Ꮎ
    0.44
    আপনার
    0.43
    POSITIVE LOGITS
    ல்
    0.56
    ৃত
    0.50
    もっと
    0.46
    ರ್
    0.45
    x
    0.45
    ha
    0.44
    Más
    0.44
    یک
    0.43
    autoarima
    0.43
    varande
    0.43
    Activations Density 0.000%

    No Known Activations