© 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. 253336
    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
    ativity
    0.55
     बधाई
    0.51
    రగ
    0.50
    udder
    0.48
    Complexity
    0.48
     बायोलॉजी
    0.48
    蜼
    0.47
    सादर
    0.47
    собенно
    0.47
     चोट
    0.47
    POSITIVE LOGITS
     dissol
    0.58
    ’
    0.55
     unscrupulous
    0.52
     multifunctional
    0.52
     barter
    0.49
     estr
    0.49
     benzyl
    0.48
     turbulent
    0.47
     lia
    0.47
     termin
    0.46
    Activations Density 0.000%

    No Known Activations