© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 224126
    Prev
    Next
    INDEX
    Explanations

    friendly pricing, particular piece, plenary session

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

    abstract concepts and analogies

    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
    ଣ
    0.52
    㓈
    0.52
     horaires
    0.50
    ورہ
    0.50
     napkins
    0.49
    ພວກເຮ
    0.48
    镭
    0.47
    也就是说
    0.47
     hamburgers
    0.47
    銑
    0.47
    POSITIVE LOGITS
    -
    0.70
    sean
    0.52
    est
    0.51
    Ó
    0.47
    ÍA
    0.46
    5
    0.46
    -#
    0.46
    <b>
    0.45
    stract
    0.45
    ter
    0.45
    Activations Density 0.000%

    No Known Activations