© 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. 260282
    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
    '
    0.52
     byrow
    0.50
     eigen
    0.48
    っているので
    0.47
    (
    0.46
    の値
    0.45
    getAttribute
    0.45
     применяется
    0.44
    ],
    0.43
     equivalently
    0.43
    POSITIVE LOGITS
    dokument
    0.50
     चट
    0.49
     सुर्खियों
    0.47
    吩
    0.46
    Mein
    0.46
    surfing
    0.46
    淝
    0.46
     memer
    0.45
     Susana
    0.45
     journalists
    0.44
    Activations Density 0.001%

    No Known Activations