© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 254948
    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
     영향
    0.49
    鬪
    0.49
    搆
    0.48
     със
    0.46
     비슷한
    0.44
     Somewhere
    0.44
    와의
    0.43
    終了
    0.43
     toutefois
    0.43
     혹은
    0.42
    POSITIVE LOGITS
    agno
    0.45
    ani
    0.43
    ena
    0.43
    aft
    0.43
    ⁩
    0.43
     proceeding
    0.42
    asin
    0.42
    enet
    0.42
    xi
    0.42
    ப்பட்டுள்ள
    0.42
    Activations Density 0.000%

    No Known Activations