© 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. 195763
    Prev
    Next
    INDEX
    Explanations

    listing alternatives or options

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

    or and

    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
     academia
    0.47
    ocl
    0.47
    स्ट्रेट
    0.46
    umbles
    0.45
    িয়৷
    0.45
     కృ
    0.44
     efficiently
    0.44
    adas
    0.43
     बर्फ
    0.43
    ঞ্চি
    0.43
    POSITIVE LOGITS
    ו
    0.57
    หรือ
    0.54
     парни
    0.51
     ወይም
    0.48
    orty
    0.46
    或其他
    0.46
     hoặc
    0.46
     ترى
    0.45
     или
    0.45
     ಅಥವಾ
    0.44
    Activations Density 0.000%

    No Known Activations