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. 8378
    Prev
    Next
    INDEX
    Explanations

    version numbers and builds

    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
     discussions
    -0.87
    一台
    -0.73
    Zgod
    -0.72
     aprecia
    -0.71
     recompensa
    -0.71
    さっそく
    -0.71
     blanda
    -0.71
     disputes
    -0.71
    乘坐
    -0.70
    啫
    -0.70
    POSITIVE LOGITS
    Revision
    0.84
    revision
    0.84
     Revision
    0.81
     Builds
    0.81
    Build
    0.81
     revision
    0.80
     build
    0.80
     Extra
    0.80
     Packet
    0.79
     ECTS
    0.79
    Activations Density 0.003%

    No Known Activations