© 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. 249231
    Prev
    Next
    INDEX
    Explanations

    see also

    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
     अथवा
    0.55
    あるいは
    0.55
    하거나
    0.54
     અથવા
    0.52
    或者是
    0.51
    EnglishMarks
    0.51
    ۥ
    0.50
     அல்லது
    0.49
    রূপে
    0.48
     ಅಥವಾ
    0.48
    POSITIVE LOGITS
     I
    0.51
     dodgy
    0.50
     ayer
    0.50
     upward
    0.49
     Angie
    0.49
    !
    0.49
    ைத்
    0.49
     async
    0.48
    Nigerian
    0.48
     upload
    0.48
    Activations Density 0.001%

    No Known Activations