© 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. 34145
    Prev
    Next
    INDEX
    Explanations

    home, today, now, title, weight

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

    pronouns and possessives

    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
     /
    0.55
     "
    0.55
    \
    0.54
     বৎসর
    0.53
     উক্ত
    0.53
    !!!!!
    0.50
    อ
    0.50
     उपरोक्त
    0.50
    /
    0.50
     +
    0.49
    POSITIVE LOGITS
     माझ्या
    0.66
    ।”
    0.63
     எங்கள்
    0.63
     મારા
    0.62
     நாங்கள்
    0.61
     мои
    0.61
     हमारी
    0.59
    我和
    0.59
     minhas
    0.57
     আমি
    0.57
    Activations Density 0.089%

    No Known Activations