© 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. 50960
    Prev
    Next
    INDEX
    Explanations

    common pairings and sequences

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

    explaining things and processes

    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
    Bible
    0.50
    勂
    0.48
    Checkout
    0.47
    σίας
    0.46
    Letter
    0.46
    Coach
    0.46
    שט
    0.45
    Off
    0.44
    ikai
    0.44
    Curve
    0.44
    POSITIVE LOGITS
     sehingga
    0.47
     noc
    0.46
     وبالتالي
    0.46
     hangi
    0.46
     കമ്മി
    0.46
     unfortunate
    0.45
     幅
    0.45
     feria
    0.44
     パンツ
    0.44
    weiter
    0.43
    Activations Density 0.000%

    No Known Activations