© 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. 138447
    Prev
    Next
    INDEX
    Explanations

    common word co-occurrences

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

    controls, level, and January

    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
     문화
    0.48
     ro
    0.44
     சர்ச்ச
    0.43
     계획
    0.43
     நாடு
    0.43
    ে
    0.42
    COMING
    0.41
     বাহুল্য
    0.41
     trọng
    0.41
     safeguard
    0.41
    POSITIVE LOGITS
    सीपी
    0.49
    স্থানে
    0.48
    Alexa
    0.48
    /***
    0.48
    व्यव
    0.47
    حبه
    0.47
    zg
    0.47
    Чи
    0.47
    XP
    0.46
    JFrame
    0.46
    Activations Density 0.001%

    No Known Activations