© 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. 206206
    Prev
    Next
    INDEX
    Explanations

    surfaces, tray, help, excellence, seen, admission, born

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

    curiosity about new things

    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
     Phang
    0.48
     abundances
    0.48
    ٹے
    0.47
    емого
    0.47
     प्रभावशाली
    0.46
    ழிய
    0.45
    ඨ
    0.45
     hoặc
    0.44
    ة
    0.44
     പ്രതീ
    0.43
    POSITIVE LOGITS
    LIFE
    0.47
    body
    0.45
    iu
    0.45
    mechan
    0.45
    PRO
    0.44
    mechanical
    0.44
    il
    0.43
    chi
    0.43
    collection
    0.43
     CERT
    0.43
    Activations Density 0.000%

    No Known Activations