© 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. 258852
    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
    ↵
    0.46
     Medical
    0.41
     Athletic
    0.40
     Firearms
    0.40
     Motor
    0.39
     Handball
    0.39
    (
    0.38
     Muscle
    0.38
     Cau
    0.38
     Parking
    0.38
    POSITIVE LOGITS
    мета
    0.42
     каталог
    0.38
    fragen
    0.38
     கேள்
    0.37
     ಸಂಗ
    0.37
    𝘭
    0.37
    เย
    0.36
    к
    0.36
    विचार
    0.36
    𝖚
    0.36
    Activations Density 0.009%

    No Known Activations