© 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. 258117
    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
     ऑगस्ट
    0.51
    August
    0.49
     geochemistry
    0.46
    whal
    0.44
    t
    0.44
     preservation
    0.43
    獒
    0.43
    鸮
    0.43
    Illuminate
    0.42
     কংগ্রেস
    0.42
    POSITIVE LOGITS
    unkte
    0.46
     সাফল
    0.45
    Titles
    0.45
    acement
    0.44
    εσ
    0.44
    (*)
    0.43
    ροσ
    0.42
     Tide
    0.42
     normalen
    0.42
     Level
    0.42
    Activations Density 0.002%

    No Known Activations