© 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. 174139
    Prev
    Next
    INDEX
    Explanations

    transit and location words

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

    environmentally conscious people

    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
     creativo
    0.50
     〢
    0.45
    긍
    0.44
    ب
    0.43
     ಉತ್ತಮ
    0.43
    ف
    0.43
     creativa
    0.43
    ARCHIVO
    0.43
    بن
    0.43
    вано
    0.42
    POSITIVE LOGITS
     μετα
    0.46
     hospital
    0.46
    seh
    0.44
    <
    0.44
     seide
    0.44
     <
    0.43
    stasy
    0.43
     system
    0.42
     interior
    0.42
     samt
    0.42
    Activations Density 0.001%

    No Known Activations