© 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. 150387
    Prev
    Next
    INDEX
    Explanations

    cost-benefit calculations

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

    location, future, or lunch

    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
     derel
    0.48
     shire
    0.44
     computer
    0.43
     topographical
    0.43
     uniformed
    0.42
    컴
    0.42
     comet
    0.42
     cyberspace
    0.42
     mainframe
    0.41
    旲
    0.41
    POSITIVE LOGITS
     μεγαλύτε
    0.53
     подума
    0.48
    ভালো
    0.47
    Nak
    0.46
     ძალიან
    0.45
     গুরুত্বপূর্ণ
    0.45
     ভালোভাবে
    0.45
     différente
    0.45
     pozw
    0.44
     Então
    0.44
    Activations Density 0.001%

    No Known Activations