© 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. 232859
    Prev
    Next
    INDEX
    Explanations

    game rounds ordering current

    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
     gorgeous
    0.50
    亮
    0.47
    ครอง
    0.46
     cantik
    0.46
    Gorgeous
    0.46
    绚
    0.46
     dodgy
    0.45
    pon
    0.44
    QS
    0.43
    ɑ
    0.43
    POSITIVE LOGITS
     energii
    0.45
     urging
    0.45
     absorbance
    0.45
     increase
    0.45
     apathy
    0.43
     sentimento
    0.42
     ensuring
    0.42
    増加
    0.42
    शिक्षा
    0.41
     Goshen
    0.41
    Activations Density 0.001%

    No Known Activations