© 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. 177594
    Prev
    Next
    INDEX
    Explanations

    sheriff career Spirit Matthew racially reach

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

    questions about safety and use

    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
     СА
    0.46
    ۞
    0.43
    ázej
    0.43
    臀
    0.43
     ناس
    0.41
     ধর্ষ
    0.41
    覺得
    0.41
     факти
    0.41
    fahrer
    0.41
    髀
    0.41
    POSITIVE LOGITS
     anuv
    0.47
     khel
    0.47
    문
    0.47
     panoramic
    0.46
    ड
    0.46
     Keegan
    0.45
     voicemail
    0.45
     aeration
    0.44
    ट्यूब
    0.44
     stifle
    0.44
    Activations Density 0.001%

    No Known Activations