© 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. 217721
    Prev
    Next
    INDEX
    Explanations

    threatened, readers, laughed, challenged

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

    multi-layer structure

    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
     Tables
    0.46
     në
    0.46
     auprès
    0.45
     Summary
    0.45
     Engines
    0.44
     Text
    0.44
    <0xE3>
    0.44
     New
    0.44
     Finger
    0.43
     biography
    0.43
    POSITIVE LOGITS
    푎
    0.50
     дав
    0.50
    क्रा
    0.50
     charmed
    0.48
    HasStarred
    0.47
     striated
    0.47
     частично
    0.46
    catalyzed
    0.46
     взаимодействия
    0.45
    challenged
    0.45
    Activations Density 0.001%

    No Known Activations