© 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. 149547
    Prev
    Next
    INDEX
    Explanations

    foreign and tech terms

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

    computer jargon and technical terms

    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
     cultivators
    0.53
     axles
    0.50
     refineries
    0.47
    合理的
    0.46
     earthen
    0.45
     petal
    0.45
    薀
    0.44
    意義
    0.44
     reflectors
    0.44
     stalks
    0.43
    POSITIVE LOGITS
    Laptop
    0.50
     Laptop
    0.49
     momencie
    0.47
     Passwort
    0.47
     Facial
    0.46
     Login
    0.46
    Xamarin
    0.46
    '>
    0.45
     Smartphones
    0.45
     Gazetteer
    0.45
    Activations Density 0.002%

    No Known Activations