© 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. 61920
    Prev
    Next
    INDEX
    Explanations

    punctuation and common phrases

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

    references and technical terms

    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
     magma
    0.48
     Drupal
    0.48
     ฟัง
    0.48
    -------
    0.47
     Minecraft
    0.47
     Canva
    0.47
     Olivia
    0.47
    ^{*
    0.47
    --
    0.46
     boast
    0.45
    POSITIVE LOGITS
    ка
    0.55
    صل
    0.52
    ология
    0.52
    ティング
    0.49
    乆
    0.48
    NOTA
    0.48
    aciji
    0.48
    ﺲ
    0.47
    ROUTES
    0.46
    ب
    0.46
    Activations Density 0.000%

    No Known Activations