© 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. 175502
    Prev
    Next
    INDEX
    Explanations

    school level, used for, closed following

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

    reduz idas

    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
     Borders
    0.49
     Buds
    0.47
     Understanding
    0.47
    🕍
    0.47
     Data
    0.46
     Writing
    0.46
     Mega
    0.45
    嘅
    0.45
    
    0.45
     Would
    0.45
    POSITIVE LOGITS
     apariencia
    0.53
    arli
    0.50
     целый
    0.49
    alit
    0.49
     تحد
    0.48
     коло
    0.48
     مزاح
    0.48
    ranet
    0.47
    ute
    0.47
    objeto
    0.47
    Activations Density 0.000%

    No Known Activations