© 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. 233518
    Prev
    Next
    INDEX
    Explanations

    state laws, shall, tea, behold

    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
     typical
    0.43
    これから
    0.43
    ಕ್ಸ್
    0.43
    ING
    0.42
     типи
    0.42
    思
    0.42
     crowded
    0.41
     complementary
    0.41
     frequented
    0.41
    わけで
    0.41
    POSITIVE LOGITS
     तेल
    0.52
    ecido
    0.47
    yaa
    0.47
    🍚
    0.46
    ebilir
    0.46
    reden
    0.46
     caza
    0.46
    liter
    0.46
    direita
    0.46
     producteurs
    0.46
    Activations Density 0.001%

    No Known Activations