© 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. 181745
    Prev
    Next
    INDEX
    Explanations

    American supervision

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

    nearby organs

    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
    ления
    0.53
     analyses
    0.50
    峀
    0.49
    ール
    0.49
     workouts
    0.48
     outings
    0.48
     ακό
    0.48
     estimations
    0.47
     observable
    0.47
     interruption
    0.46
    POSITIVE LOGITS
     जरिए
    0.51
    backend
    0.47
    QC
    0.46
     Mikey
    0.45
     加
    0.45
    Ə
    0.45
     ח
    0.44
     Rada
    0.44
     दिल्‍ली
    0.44
    נטי
    0.44
    Activations Density 0.001%

    No Known Activations