© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15073
    Prev
    Next
    INDEX
    Explanations

    Spanish words related to activities/places

    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_262k_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
    绝
    0.50
    報酬
    0.48
    絕
    0.47
    restling
    0.47
    🏈
    0.47
     vuttam
    0.45
     graduellement
    0.45
    🏒
    0.45
    UNICATIONS
    0.45
    人類
    0.44
    POSITIVE LOGITS
     gastronomy
    0.62
     aromat
    0.61
     gastronomic
    0.59
     confectionery
    0.57
     hoş
    0.54
     pa
    0.54
     hygienic
    0.54
     sociable
    0.54
     terrace
    0.54
     venous
    0.54
    Activations Density 0.046%

    No Known Activations