© 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. 257369
    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
    ize
    0.53
     cap
    0.48
    ci
    0.46
    uz
    0.46
    ized
    0.44
    tey
    0.44
    ado
    0.44
    ଳ
    0.44
    anz
    0.43
    ley
    0.43
    POSITIVE LOGITS
     évolution
    0.55
    ദം
    0.54
     preuve
    0.52
     erreur
    0.49
    рда
    0.48
     dipende
    0.48
    ﮅ
    0.47
     économ
    0.47
     schéma
    0.47
    த்தைக்
    0.47
    Activations Density 0.001%

    No Known Activations