© 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. 97852
    Prev
    Next
    INDEX
    Explanations

    historical and religious context

    np_acts-logits-general · gemini-2.5-flash-lite

    magic and fantasy descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     contradicting
    0.50
    ದ
    0.49
     இறந்த
    0.45
    қда
    0.44
    гляд
    0.44
     eloquently
    0.43
    ની
    0.42
     eğer
    0.42
    晧
    0.42
     discrep
    0.42
    POSITIVE LOGITS
    newTask
    0.45
    薹
    0.45
     bulkhead
    0.44
    json
    0.44
     $"
    0.44
     Talon
    0.43
     Rebels
    0.42
     Score
    0.42
     Lieutenant
    0.42
     furl
    0.42
    Activations Density 0.001%

    No Known Activations