© 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. 13680
    Prev
    Next
    INDEX
    Explanations

    expressions of interest, any sort of

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

    morning flow

    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
     krypt
    0.46
    全世界
    0.46
    inn
    0.45
    ult
    0.44
    想要
    0.43
    嘶
    0.43
    je
    0.42
    destroyed
    0.42
    thereum
    0.42
     heartbreak
    0.42
    POSITIVE LOGITS
     variétés
    0.54
     firstname
    0.50
     proizvoda
    0.50
     parmi
    0.47
     محصولات
    0.46
     marries
    0.45
     روستا
    0.45
    Ა
    0.45
    ？
    0.45
     marrying
    0.44
    Activations Density 0.000%

    No Known Activations