© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245642
    Prev
    Next
    INDEX
    Explanations

    following terms with descriptors

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ме
    0.53
    وى
    0.52
    на
    0.52
     ሜ
    0.51
     던
    0.51
     subter
    0.48
    де
    0.47
     powied
    0.47
     کریم
    0.47
    дык
    0.47
    POSITIVE LOGITS
     Korea
    0.46
     taraf
    0.45
    全体
    0.41
     Sole
    0.41
     trist
    0.40
    typical
    0.40
    land
    0.39
    عتها
    0.39
    \}}
    0.39
     overall
    0.38
    Activations Density 0.000%

    No Known Activations