© 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. 254669
    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
    琅
    0.48
    ্যাম্প
    0.48
    จาก
    0.45
    ゲル
    0.45
     intrinsically
    0.45
     '',
    0.44
    JAK
    0.44
     {},
    0.43
     Уен
    0.43
     SILVER
    0.43
    POSITIVE LOGITS
    filtration
    0.46
    ти
    0.45
    ä
    0.45
     सीटेट
    0.44
     सहकारी
    0.44
     declarar
    0.44
    ig
    0.43
    ces
    0.42
     сохранения
    0.42
    Clear
    0.42
    Activations Density 0.000%

    No Known Activations