© 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. 81120
    Prev
    Next
    INDEX
    Explanations

    collection the, you like, Collins for

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

    drink and hydration category

    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
    avers
    0.47
     ثالث
    0.45
     Schä
    0.44
    фициа
    0.43
     destroyed
    0.43
     dermat
    0.43
    }>{
    0.43
     ভট্ট
    0.43
    {})
    0.42
     пам
    0.42
    POSITIVE LOGITS
    ა
    0.49
    વા
    0.49
    ی
    0.48
     INDEX
    0.47
     อื่น
    0.47
     არის
    0.46
     nee
    0.46
    渓
    0.46
    िया
    0.46
     Genes
    0.46
    Activations Density 0.000%

    No Known Activations