© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10800
    Prev
    Next
    INDEX
    Explanations

    exp- prefixed words

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

    expedition exploitative exposomics exploited

    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_40_width_16k_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
     Aham
    0.49
    ahas
    0.47
    aham
    0.47
    क्ट
    0.46
    apie
    0.46
    ань
    0.46
    ewek
    0.45
    ನ
    0.45
    न
    0.45
    alop
    0.45
    POSITIVE LOGITS
     exp
    0.97
     एक्सप
    0.87
     EXP
    0.87
     Exp
    0.86
     expos
    0.79
     expo
    0.78
     Expos
    0.77
     Expo
    0.77
     eksp
    0.73
    EXP
    0.73
    Activations Density 0.126%

    No Known Activations