© 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. 257245
    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
     μια
    0.48
     faithfulness
    0.47
    随机
    0.46
    俅
    0.44
    俎
    0.43
    밧
    0.43
     halting
    0.42
    ிக
    0.41
    दोस्तों
    0.41
    誑
    0.41
    POSITIVE LOGITS
    EL
    0.52
     arte
    0.51
    F
    0.49
    ra
    0.48
     J
    0.47
    ，
    0.47
    r
    0.46
    G
    0.46
     fern
    0.46
     F
    0.45
    Activations Density 0.001%

    No Known Activations