© 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. 21243
    Prev
    Next
    INDEX
    Explanations

    actions and possessives

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

    historical context and modern conditions

    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
     spearheaded
    0.50
    ’
    0.39
    9
    0.38
    4
    0.37
     superstar
    0.37
    非常
    0.36
    5
    0.36
     blockbuster
    0.36
    7
    0.35
     unrival
    0.35
    POSITIVE LOGITS
     நடவடிக்கைகள்
    0.36
     arbete
    0.36
     ಕೆಲಸ
    0.36
     saz
    0.35
     colds
    0.35
     viciss
    0.35
     प्रयत्न
    0.34
     distaste
    0.34
     பாதுகாக்க
    0.34
    䂘
    0.34
    Activations Density 0.008%

    No Known Activations