© 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. 254436
    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
    篌
    0.52
    ოლო
    0.52
    ورسٹی
    0.50
    elevationMap
    0.50
    맛
    0.49
    헙
    0.49
    ሢ
    0.48
    Methylsulfanyl
    0.48
    Биография
    0.48
    훔
    0.48
    POSITIVE LOGITS
     equilibrio
    0.46
    thinkable
    0.43
    ature
    0.43
     It
    0.42
     Visit
    0.42
    idding
    0.42
     तूफान
    0.41
    $)
    0.40
     barking
    0.39
     Storm
    0.39
    Activations Density 0.000%

    No Known Activations