© 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. 115581
    Prev
    Next
    INDEX
    Explanations

    chef's tasting menu options

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

    menu and meal plans

    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
     foodie
    0.52
    醬
    0.47
     gastronomic
    0.46
    맛집
    0.46
     mango
    0.45
     sushi
    0.45
    invention
    0.44
    検索
    0.43
     moj
    0.43
    烤
    0.41
    POSITIVE LOGITS
    Choice
    0.45
     Choice
    0.45
    ALTERN
    0.44
    替代
    0.43
     POA
    0.42
     BULLETIN
    0.42
     indeterm
    0.42
    代替
    0.42
     연속
    0.41
     제시
    0.41
    Activations Density 0.139%

    No Known Activations