© 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. 18799
    Prev
    Next
    INDEX
    Explanations

    stating or saying

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

    speaking or asserting viewpoints

    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
    現在
    0.44
     Kimber
    0.44
    现在
    0.42
    如今
    0.42
    DETAILS
    0.42
    বর্তমানে
    0.41
    😵
    0.41
    푞
    0.39
     चीजें
    0.39
    英語版
    0.39
    POSITIVE LOGITS
     saying
    0.61
     فقال
    0.60
     કહ્યું
    0.57
     وقال
    0.57
     বলেছে
    0.54
     emphatically
    0.53
     বলেছিল
    0.52
     کہا
    0.52
     বলেছিলেন
    0.51
     म्हणाले
    0.51
    Activations Density 0.021%

    No Known Activations