© 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. 259005
    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
    ي
    0.86
     vó
    0.67
    т
    0.64
    ت
    0.64
    𐰆
    0.64
    ів
    0.64
    كثر
    0.63
    ه
    0.63
    人
    0.63
    י
    0.63
    POSITIVE LOGITS
     Kingdom
    0.83
     King
    0.74
     royaume
    0.73
    Royal
    0.71
    Kingdom
    0.70
     Royal
    0.70
    King
    0.70
    Crown
    0.69
     Crown
    0.69
     Queen
    0.68
    Activations Density 0.238%

    No Known Activations