© 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. 57509
    Prev
    Next
    INDEX
    Explanations

    mentioning school restorations

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

    sequence clauses

    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
    原生
    0.46
    圈
    0.46
    贼
    0.45
    기의
    0.44
    Loss
    0.43
    POR
    0.43
    ID
    0.43
    惺
    0.42
    لم
    0.42
    зирован
    0.42
    POSITIVE LOGITS
     railway
    0.52
     pharmacy
    0.50
     covariance
    0.50
     biomarker
    0.50
     oncology
    0.50
     bimodule
    0.50
     wonderful
    0.50
     tour
    0.49
    므로
    0.49
     ravine
    0.48
    Activations Density 0.000%

    No Known Activations