© 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. 12487
    Prev
    Next
    INDEX
    Explanations

    levels and stages

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

    categorizing by complexity or level

    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
     Bren
    0.49
    ভিড
    0.48
     উপকারী
    0.45
    ftime
    0.45
    tmp
    0.44
     Tahun
    0.43
     冬
    0.43
    റോ
    0.43
     Kloster
    0.43
    btnInventory
    0.42
    POSITIVE LOGITS
     level
    1.71
    level
    1.52
     levels
    1.51
    级别
    1.51
     niveau
    1.48
    Level
    1.45
     LEVEL
    1.43
    ระดับ
    1.41
     nivel
    1.39
    レベル
    1.38
    Activations Density 0.188%

    No Known Activations