© 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. 254336
    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
     เส
    0.49
    த்தையும்
    0.49
     такую
    0.48
    ลีก
    0.48
     ..$
    0.47
     ..,
    0.47
    owości
    0.46
    %,
    0.46
     GUIContent
    0.45
     आध्यात्मिक
    0.45
    POSITIVE LOGITS
     anúncios
    0.46
     initiale
    0.46
     ornith
    0.45
     histoire
    0.45
    fw
    0.44
    SLOW
    0.44
    manuel
    0.43
     ancienne
    0.42
    髻
    0.42
     iniz
    0.41
    Activations Density 0.000%

    No Known Activations