© 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. 151492
    Prev
    Next
    INDEX
    Explanations

    OEM compatibility

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

    XYZ Technologies

    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
    č
    0.51
    you
    0.50
    we
    0.48
    so
    0.48
    со
    0.46
    с
    0.44
    iend
    0.43
    춤
    0.41
    oč
    0.41
    isering
    0.40
    POSITIVE LOGITS
    ပြီး
    0.46
     limitée
    0.43
    েরিক
    0.43
     indiqu
    0.43
     wishlist
    0.42
    Trad
    0.41
     offline
    0.41
     ড্র
    0.41
     আক্রান্ত
    0.41
    Miscellaneous
    0.41
    Activations Density 0.003%

    No Known Activations