© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49345
    Prev
    Next
    INDEX
    Explanations

    automotive terms and vehicles

    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_65k_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
     গু
    0.46
     glassware
    0.42
    甜
    0.42
     countertop
    0.42
     Sweet
    0.41
     बर्तन
    0.41
     Navy
    0.40
     Dairy
    0.40
     sweet
    0.40
     Handmade
    0.40
    POSITIVE LOGITS
     automotive
    0.93
     Automotive
    0.84
     automaker
    0.79
    Vehicle
    0.74
    🚘
    0.73
    汽车
    0.73
     automakers
    0.73
     автомоби
    0.72
    automobile
    0.71
     automobil
    0.71
    Activations Density 0.117%

    No Known Activations