Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8287
    Prev
    Next
    INDEX
    Explanations

    tires and road condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iprot
    -0.80
     Auft
    -0.76
    رائه
    -0.73
    apatkan
    -0.72
     UTIL
    -0.70
    atoria
    -0.69
    PMailer
    -0.68
    ("")]
    -0.67
    ulence
    -0.67
     materiais
    -0.67
    POSITIVE LOGITS
     sticky
    0.98
    sticky
    0.91
     square
    0.78
    Patches
    0.73
     crisp
    0.71
     perish
    0.71
    뾰
    0.70
     geisti
    0.69
     section
    0.69
    扁平
    0.68
    Activations Density 0.012%

    No Known Activations