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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13602
    Prev
    Next
    INDEX
    Explanations

    bold writing and concepts

    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
     Staub
    0.41
     Wink
    0.41
     nahil
    0.40
    ps
    0.40
    qda
    0.40
    *[
    0.40
    *;
    0.39
    "),(
    0.38
     রোগীদের
    0.38
    RSSI
    0.38
    POSITIVE LOGITS
    Bold
    0.77
     bold
    0.77
     Bold
    0.70
     bolder
    0.61
    bold
    0.59
    italic
    0.56
     шриф
    0.54
     italic
    0.52
    faced
    0.50
     boldly
    0.47
    Activations Density 0.003%

    No Known Activations