© 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. 153350
    Prev
    Next
    INDEX
    Explanations

    member of The

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

    applicable products, toxicity, hardware, distribution, universal rule

    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
    Negative Logits
    xssf
    0.46
    Framebuffer
    0.46
     tą
    0.45
    膘
    0.45
     ضر
    0.44
     But
    0.44
    讷
    0.42
     पीडीएफ
    0.42
     تصوی
    0.42
     [.
    0.41
    POSITIVE LOGITS
    ່າຍ
    0.46
    地點
    0.46
    ἢ
    0.45
    ETARY
    0.45
    στηκε
    0.44
     bahawa
    0.42
     iaitu
    0.42
     antibacterial
    0.41
     Đình
    0.41
    εται
    0.40
    Activations Density 0.000%

    No Known Activations