© 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. 237930
    Prev
    Next
    INDEX
    Explanations

    globally significant

    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
    employ
    0.45
    Instance
    0.45
    ยายาม
    0.43
    Termination
    0.43
    क्रोश
    0.43
    꺽
    0.43
    Definitions
    0.42
    Acknowledgement
    0.42
    谓
    0.42
    separation
    0.42
    POSITIVE LOGITS
     Zim
    0.50
     Yemek
    0.50
     zim
    0.49
     Geschäft
    0.49
     tash
    0.48
     umfasst
    0.48
     fehlen
    0.48
     և
    0.47
     Bt
    0.47
     führt
    0.47
    Activations Density 0.000%

    No Known Activations