© 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. 234762
    Prev
    Next
    INDEX
    Explanations

    countries, store, interface, parents, balance

    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
    мета
    0.50
    ុត
    0.50
    Proven
    0.49
    の前
    0.49
    ರಿಸ
    0.48
    Animals
    0.47
    и
    0.47
    Kyr
    0.47
    Wear
    0.46
    KSprite
    0.45
    POSITIVE LOGITS
     fundament
    0.50
     Edith
    0.46
     条
    0.46
     Dojo
    0.45
     când
    0.45
     Variety
    0.45
     Avalon
    0.44
     Fundamental
    0.44
     ESTIM
    0.44
     fundamento
    0.44
    Activations Density 0.001%

    No Known Activations