© 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. 257473
    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
     Contribution
    0.42
     болез
    0.41
    睑
    0.39
    மற்ற
    0.39
    ester
    0.38
     Faces
    0.38
     femme
    0.38
    л
    0.38
     Range
    0.38
    ก
    0.37
    POSITIVE LOGITS
     backpacking
    0.55
     quinoa
    0.52
    candidate
    0.50
     dishes
    0.49
     acaba
    0.48
    Ŷ
    0.48
    batasan
    0.47
    アウトドア
    0.45
    Candidate
    0.45
    katana
    0.45
    Activations Density 0.001%

    No Known Activations