© 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. 260329
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ^{*}\
    0.48
     единственный
    0.47
    df
    0.47
     Golub
    0.46
     biochem
    0.45
     Artur
    0.45
    Seite
    0.44
     अभिय
    0.44
     coleg
    0.44
     Olympi
    0.44
    POSITIVE LOGITS
    भाग
    0.46
     exploring
    0.46
    徜
    0.45
    ट्टा
    0.45
    atil
    0.44
    мок
    0.44
    ین
    0.43
    議論
    0.42
    ين
    0.42
    ن
    0.42
    Activations Density 0.000%

    No Known Activations