© 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. 251237
    Prev
    Next
    INDEX
    Explanations

    multilingual contexts

    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
     wf
    0.46
    ADER
    0.44
    ﭘ
    0.42
    ERN
    0.41
     integra
    0.41
     AS
    0.41
    iritual
    0.41
    bedarf
    0.41
     Abgerufen
    0.41
     stage
    0.40
    POSITIVE LOGITS
     ಕ
    0.57
     বিব্রত
    0.50
    lerinin
    0.48
     വെള്ള
    0.48
     izinsuku
    0.48
     cốc
    0.47
     مۇ
    0.47
    ပေ
    0.47
     ಲೋ
    0.47
     င
    0.47
    Activations Density 0.001%

    No Known Activations