© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48051
    Prev
    Next
    INDEX
    Explanations

    cost and value comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     -
    0.51
     Snow
    0.50
     half
    0.49
     (
    0.49
     inner
    0.48
     war
    0.47
     m
    0.46
     u
    0.46
     snow
    0.46
     battle
    0.46
    POSITIVE LOGITS
     notificações
    0.57
    యితే
    0.49
    メージ
    0.49
    店舗
    0.48
    ヨタ
    0.48
     Porém
    0.48
    steuer
    0.47
    kfollowers
    0.47
    луйста
    0.47
    etään
    0.47
    Activations Density 0.002%

    No Known Activations