© 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. 89440
    Prev
    Next
    INDEX
    Explanations

    money, rental, intelligence, tension, conditioning

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

    not necessarily

    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
    ('
    0.48
     inaccur
    0.47
    अ
    0.46
     '
    0.46
     прави
    0.46
     Dos
    0.46
    '[
    0.44
     '=
    0.43
     Acosta
    0.42
    Dos
    0.42
    POSITIVE LOGITS
    ೇನೆ
    0.46
     rental
    0.44
    каў
    0.44
     diterapkan
    0.44
     দিয়েছিলেন
    0.43
    خیص
    0.43
     Rental
    0.43
    િયન
    0.43
     svol
    0.42
    رائی
    0.42
    Activations Density 0.000%

    No Known Activations