© 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. 258176
    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
     बल्ब
    0.49
     termasuk
    0.49
    ج
    0.46
     bhan
    0.46
    اد
    0.45
     ¨
    0.45
    AHN
    0.45
     awal
    0.44
     Rehman
    0.44
    ܬ
    0.44
    POSITIVE LOGITS
     unload
    0.48
     effluents
    0.46
     switchTo
    0.45
    વાથી
    0.44
     optimize
    0.44
     wealthier
    0.43
    iming
    0.42
     నేపథ్యంలో
    0.42
     rodents
    0.41
     retain
    0.41
    Activations Density 0.000%

    No Known Activations