© 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. 177616
    Prev
    Next
    INDEX
    Explanations

    date night, sweet oil, plague cure

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

    "most restorative" or "highly distorted"

    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
    unread
    0.53
     ច
    0.49
    ichte
    0.46
    वरील
    0.46
    aito
    0.46
    ﺪ
    0.46
    、$
    0.45
     جي
    0.45
    iche
    0.44
     люд
    0.44
    POSITIVE LOGITS
     ACR
    0.48
     imputation
    0.46
     A
    0.46
    (
    0.46
    varo
    0.44
     quantum
    0.43
     Medical
    0.43
     exemplaire
    0.43
     I
    0.43
    ນີ້
    0.43
    Activations Density 0.000%

    No Known Activations