© 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. 250907
    Prev
    Next
    INDEX
    Explanations

    earring design

    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
     TTS
    0.52
     them
    0.51
     Notation
    0.48
     BUSINESS
    0.47
     Hwy
    0.46
     to
    0.46
     punishment
    0.46
     \
    0.45
    classification
    0.45
     Institute
    0.45
    POSITIVE LOGITS
    ørt
    0.54
    ัว
    0.51
    GradientPanel
    0.51
    ലെസ്
    0.49
    amię
    0.49
    ادا
    0.48
     kinderen
    0.47
    orf
    0.46
    이드
    0.46
     ปุ่ม
    0.46
    Activations Density 0.003%

    No Known Activations