© 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. 253742
    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
    创立
    0.46
     CHLOR
    0.45
    abbanti
    0.44
    糺
    0.44
     spacerItem
    0.43
     หัด
    0.43
     መጠን
    0.43
     필요한
    0.43
    NaClO
    0.43
     シュ
    0.42
    POSITIVE LOGITS
    get
    0.48
    ES
    0.48
    es
    0.47
    s
    0.45
    presence
    0.43
     يؤ
    0.43
    gebied
    0.43
    been
    0.43
    ↵↵
    0.43
    Ί
    0.42
    Activations Density 0.000%

    No Known Activations