© 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. 91793
    Prev
    Next
    INDEX
    Explanations

    Local ®

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

    differs significantly

    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
    N
    0.50
    h
    0.49
     Ship
    0.47
    b
    0.47
     Serialize
    0.46
     Shipping
    0.46
     Compiler
    0.46
     Acceler
    0.45
     国内
    0.45
     Pharmacy
    0.44
    POSITIVE LOGITS
     باور
    0.48
     truthful
    0.47
    uzzi
    0.43
    mittance
    0.43
     विद्यार्थियों
    0.43
     perímetro
    0.42
     শ্রবণ
    0.42
    Ꮬ
    0.42
     dispersive
    0.42
    认可
    0.42
    Activations Density 0.001%

    No Known Activations