© 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. 161194
    Prev
    Next
    INDEX
    Explanations

    locations and amenities

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

    random or error messages

    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
    覂
    0.53
    avgsalary
    0.50
    ovaniyu
    0.47
     renverse
    0.47
    👜
    0.46
     desserts
    0.45
     зда
    0.45
    𝜁
    0.45
     হলিউ
    0.44
    өп
    0.43
    POSITIVE LOGITS
     Geelong
    0.45
     GameManager
    0.42
     selfishness
    0.42
     selfish
    0.42
     امروز
    0.41
     ۵
    0.41
     SRC
    0.41
     Sele
    0.40
     Bugün
    0.40
    ान्
    0.40
    Activations Density 0.001%

    No Known Activations