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. 221
    Prev
    Next
    INDEX
    Explanations

    He after punctuation

    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
     if
    -1.23
     there
    -1.16
     but
    -1.03
     this
    -1.00
     quien
    -0.98
     for
    -0.95
     If
    -0.95
    頜
    -0.94
    This
    -0.91
     Dieser
    -0.90
    POSITIVE LOGITS
     his
    2.69
     its
    2.03
     was
    1.68
     jego
    1.55
     его
    1.50
     is
    1.49
    其
    1.45
     has
    1.44
     suoi
    1.43
     अपनी
    1.34
    Activations Density 0.044%

    No Known Activations