© 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. 253160
    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
    പ്പിക്ക
    0.64
    క్ష
    0.60
    𝖔
    0.54
    ём
    0.53
     vých
    0.53
    ட்ச
    0.52
     హత్య
    0.52
    𒄷
    0.52
     క్రి
    0.52
     ትንሽ
    0.52
    POSITIVE LOGITS
     panorama
    0.53
     Panorama
    0.47
     ritual
    0.46
     Deal
    0.44
     Caffeine
    0.43
     deal
    0.42
     broker
    0.42
     Tariff
    0.42
     Resin
    0.42
     Libert
    0.41
    Activations Density 0.000%

    No Known Activations