© 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. 38788
    Prev
    Next
    INDEX
    Explanations

    explaining a situation or occurrence

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

    defining concepts or conditions

    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
    ส์
    0.54
     sekarang
    0.43
     الجمه
    0.43
     কেন
    0.42
    得很
    0.42
     DataSource
    0.41
     المخت
    0.41
    蜇
    0.41
    REAM
    0.40
    antung
    0.40
    POSITIVE LOGITS
    nú
    0.51
     dimost
    0.51
     áng
    0.50
    னால்
    0.49
    atm
    0.48
    ucc
    0.48
    killed
    0.48
     evocative
    0.47
    ளிய
    0.46
     rhinoceros
    0.46
    Activations Density 0.000%

    No Known Activations