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. 8040
    Prev
    Next
    INDEX
    Explanations

    please join our community

    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
    置く
    -0.97
     this
    -0.93
     yere
    -0.92
     ofta
    -0.91
     човек
    -0.88
     annan
    -0.87
    ually
    -0.85
    alties
    -0.85
     dette
    -0.84
     hän
    -0.84
    POSITIVE LOGITS
     start
    2.08
     Happy
    1.92
     remember
    1.83
     Remember
    1.73
    Happy
    1.71
     so
    1.70
     happy
    1.70
     whether
    1.57
     go
    1.55
     who
    1.49
    Activations Density 0.030%

    No Known Activations