© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193138
    Prev
    Next
    INDEX
    Explanations

    coupon code properly entered

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

    contract, functions, value, capacity, impartiality

    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
    ımızı
    0.48
     لان
    0.45
     rohkem
    0.44
     を
    0.44
    하여
    0.42
     subm
    0.42
    洷
    0.42
     raíces
    0.41
    㳊
    0.41
     أو
    0.41
    POSITIVE LOGITS
     underwent
    0.48
    lje
    0.45
    公斤
    0.45
    鋏
    0.44
    skcipher
    0.43
     fractured
    0.42
     Industries
    0.42
    ζ
    0.42
     ફે
    0.41
    lector
    0.41
    Activations Density 0.001%

    No Known Activations