© 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. 260042
    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
    ак
    0.55
    ίδα
    0.52
    Влади
    0.50
     Мини
    0.49
    Ш
    0.49
    ів
    0.49
    оп
    0.48
    ул
    0.47
    ил
    0.47
    يلي
    0.47
    POSITIVE LOGITS
     complain
    0.61
     farmhouse
    0.54
     dispatch
    0.54
     complaint
    0.53
     getaway
    0.52
     usher
    0.51
     dispensing
    0.51
     Company
    0.50
     finding
    0.50
     insult
    0.50
    Activations Density 0.000%

    No Known Activations