© 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. 252749
    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
     menyel
    0.50
    گنڈ
    0.48
     આર
    0.45
     miesią
    0.45
     समूह
    0.45
     ነ
    0.45
     ترکی
    0.44
    Ｅ
    0.44
     seçim
    0.43
     јо
    0.43
    POSITIVE LOGITS
    oviruses
    0.55
    frames
    0.50
    umerable
    0.48
    umper
    0.45
     derr
    0.45
    much
    0.44
     tiled
    0.43
    zul
    0.43
     sweaters
    0.43
    chomp
    0.43
    Activations Density 0.000%

    No Known Activations