© 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. 253950
    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
    ביר
    0.46
    으로
    0.45
    വിഡ്
    0.45
     mettre
    0.44
    つき
    0.44
     [{\
    0.44
    然後
    0.44
    acé
    0.44
    查看
    0.42
    વવા
    0.42
    POSITIVE LOGITS
     Մ
    0.52
     antagonists
    0.51
    Were
    0.50
    ISHED
    0.48
     storica
    0.47
     operativa
    0.47
     pastries
    0.46
     impairments
    0.46
     carbonates
    0.46
    ParamList
    0.46
    Activations Density 0.002%

    No Known Activations