© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134077
    Prev
    Next
    INDEX
    Explanations

    stating facts or definitions

    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_40_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
    —
    0.43
     ,
    0.42
    Ό
    0.41
     cuc
    0.40
    ,,
    0.39
     ,,
    0.39
     Ass
    0.38
     )
    0.38
    <blockquote>
    0.38
     wonder
    0.38
    POSITIVE LOGITS
     być
    0.57
    ว่าเป็น
    0.57
     أنها
    0.56
     being
    0.55
     أنه
    0.55
     bahwa
    0.54
     ότι
    0.54
    être
    0.53
     bahawa
    0.52
     להיות
    0.52
    Activations Density 0.038%

    No Known Activations