© 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. 3532
    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
    急性
    0.49
    ্া
    0.48
    pleted
    0.48
     utilisées
    0.47
    а
    0.47
    أ
    0.47
    ັ້ງ
    0.46
    اع
    0.45
     Исто
    0.45
    Chronic
    0.45
    POSITIVE LOGITS
    t
    0.46
     mol
    0.46
    ोत्सव
    0.46
     PAV
    0.46
     JOY
    0.46
     😎
    0.45
     EDA
    0.45
     slaying
    0.45
    ………….
    0.45
     lo
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.