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. 49
    Prev
    Next
    INDEX
    Explanations

    copyright notice, conditions met

    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
    Coordinator
    -0.80
     behövs
    -0.75
     ance
    -0.74
     tronic
    -0.74
     Bunting
    -0.73
     umbilical
    -0.73
    涜
    -0.70
     acepta
    -0.68
     sirve
    -0.68
     hjälper
    -0.68
    POSITIVE LOGITS
    انون
    0.75
    kill
    0.75
     tượng
    0.73
     considerable
    0.72
    닉
    0.71
     amiable
    0.70
     concise
    0.69
     venturing
    0.68
    kreis
    0.67
     lowest
    0.66
    Activations Density 0.040%

    No Known Activations