© 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. 254871
    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
     χωρίς
    0.49
     лиш
    0.47
     கேட்க
    0.46
     quieren
    0.45
    ebb
    0.45
     wollen
    0.45
    $\\
    0.44
    Ear
    0.44
     ανε
    0.44
     atthakath
    0.43
    POSITIVE LOGITS
    ুখে
    0.49
    ख
    0.45
    িখ
    0.45
    to
    0.45
    ny
    0.45
    erp
    0.45
     Connect
    0.45
     Kafka
    0.44
     puncak
    0.44
    তাপ
    0.44
    Activations Density 0.001%

    No Known Activations