© 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. 13113
    Prev
    Next
    INDEX
    Explanations

    Shrine Circus

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

    reporting, metrics, and operations

    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
     $[\
    0.54
     follows
    0.49
     میک
    0.48
     sylvis
    0.48
     chronique
    0.48
     fonctionnement
    0.48
     ["
    0.47
    増加
    0.46
     Verifica
    0.45
     Fannie
    0.45
    POSITIVE LOGITS
     oluşan
    0.48
    Dubai
    0.47
    6
    0.44
     oftentimes
    0.43
    งาม
    0.43
    Elephant
    0.43
    कल
    0.42
    लय
    0.41
    picable
    0.41
    ພວກເຮ
    0.41
    Activations Density 0.000%

    No Known Activations