© 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. 5349
    Prev
    Next
    INDEX
    Explanations

    real numbers

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

    functions and linear equations

    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
    nemen
    0.45
    但这
    0.42
    <0x19>
    0.41
    辦
    0.41
    祇
    0.41
    िजन
    0.41
    ोगी
    0.40
    ิม
    0.40
     那麼
    0.40
    ClFN
    0.40
    POSITIVE LOGITS
     Chevron
    0.44
     zarówno
    0.44
     glycos
    0.43
     Hain
    0.42
    <table>
    0.41
     Lipschitz
    0.41
     handcuffed
    0.40
     různých
    0.40
     Discuss
    0.40
     Kale
    0.39
    Activations Density 0.000%

    No Known Activations