© 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. 53517
    Prev
    Next
    INDEX
    Explanations

    Setter Puppies, cellular automata, Red Bull

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

    ideas, components, concepts

    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
     compds
    0.47
     aigus
    0.47
    populations
    0.47
     lekin
    0.46
    टाम
    0.45
     cropland
    0.44
    दीय
    0.44
     ϒ
    0.43
     agile
    0.43
    valence
    0.43
    POSITIVE LOGITS
    ài
    0.50
    Branch
    0.47
    Avro
    0.47
    搆
    0.46
     видели
    0.46
    Ầ
    0.46
     ошиб
    0.45
    Estate
    0.45
     BRANCH
    0.45
    Inventory
    0.45
    Activations Density 0.000%

    No Known Activations