© 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. 123565
    Prev
    Next
    INDEX
    Explanations

    sales prices, and numbers

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

    response attempting to fulfill prompt

    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
     l
    0.49
     u
    0.49
     asphalt
    0.48
     le
    0.48
     height
    0.48
     dos
    0.47
     per
    0.47
     on
    0.47
     lily
    0.47
     my
    0.46
    POSITIVE LOGITS
    剑
    0.50
    鼎
    0.49
    ᱫ
    0.47
    曙
    0.47
    證據
    0.47
    ături
    0.46
    竞争
    0.46
    േരി
    0.46
     Negotiations
    0.46
    ής
    0.45
    Activations Density 0.001%

    No Known Activations