© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6052
    Prev
    Next
    INDEX
    Explanations

    coffee shop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rept
    0.47
     antibody
    0.41
     sanction
    0.40
     provocative
    0.39
     vectorize
    0.39
     أع
    0.39
     provoke
    0.38
     [{'
    0.38
     reckless
    0.38
     дове
    0.38
    POSITIVE LOGITS
     coffee
    1.56
     Coffee
    1.55
    咖啡
    1.55
     커피
    1.49
    ☕
    1.47
    コーヒー
    1.46
    Coffee
    1.42
    coffee
    1.41
     кофе
    1.40
     Kaffee
    1.35
    Activations Density 0.202%

    No Known Activations