© 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. 86345
    Prev
    Next
    INDEX
    Explanations

    parts, segmentation, food, school

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

    imagine a or you

    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
     luchar
    0.49
     تصل
    0.45
    劶
    0.45
     اگه
    0.44
     Nascimento
    0.43
     locking
    0.43
     Nakon
    0.43
    ろ
    0.43
    しましたが
    0.42
     ಎಷ್ಟು
    0.42
    POSITIVE LOGITS
    Food
    0.54
    School
    0.46
    Recipe
    0.46
    Rustic
    0.43
    Denver
    0.42
    Grocery
    0.42
     Preschool
    0.42
     Food
    0.41
    Context
    0.41
    Adapted
    0.41
    Activations Density 0.007%

    No Known Activations