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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18917
    Prev
    Next
    INDEX
    Explanations

    page descriptions or content

    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
     बटा
    0.52
     costruito
    0.43
     ומ
    0.42
     концеп
    0.41
    ılım
    0.41
     ונ
    0.41
    粥
    0.41
     לג
    0.41
     samano
    0.40
    itario
    0.40
    POSITIVE LOGITS
    halation
    0.49
    炷
    0.45
    ൾ
    0.42
    ges
    0.42
    ak
    0.41
     conocidos
    0.41
    ফট
    0.41
     reng
    0.40
    صور
    0.40
    sh
    0.40
    Activations Density 0.001%

    No Known Activations