© 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. 75439
    Prev
    Next
    INDEX
    Explanations

    Quick foods

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

    commercial chatbots lik e ChatGPT

    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
    পরিস
    0.43
     extiende
    0.40
    پاکستان
    0.39
     영향
    0.38
    ляет
    0.38
    engined
    0.38
    |^{\
    0.37
     Legendre
    0.37
     inds
    0.37
    GING
    0.36
    POSITIVE LOGITS
    ualmente
    0.43
     оку
    0.42
     aloe
    0.41
    犬
    0.41
     メル
    0.41
    ぶりに
    0.41
    ема
    0.40
    мок
    0.39
    teros
    0.38
     ∀
    0.38
    Activations Density 0.000%

    No Known Activations