© 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. 31456
    Prev
    Next
    INDEX
    Explanations

    salads and dressing

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

    cold salad

    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
     boilers
    0.66
    蒸汽
    0.63
    湯
    0.61
    Heating
    0.59
    STEAM
    0.58
     boiler
    0.57
     cauldron
    0.56
    ♨
    0.56
    鍋
    0.55
    スープ
    0.55
    POSITIVE LOGITS
     salads
    0.79
     salad
    0.75
     सलाद
    0.69
    🥗
    0.68
     Cucumber
    0.68
     cucumber
    0.67
     cucumbers
    0.66
     Salad
    0.65
     chilled
    0.61
     pickle
    0.61
    Activations Density 0.141%

    No Known Activations