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. 8447
    Prev
    Next
    INDEX
    Explanations

    end of sentence or phrase

    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
     The
    -1.55
     Therefore
    -1.45
    🙄
    -1.40
    Ṭ
    -1.39
     Similarly
    -1.38
     Arquivado
    -1.36
    ĭ
    -1.34
    😄
    -1.33
     (
    -1.31
    😲
    -1.31
    POSITIVE LOGITS
    ↵↵
    3.67
    <eos>
    1.81
    ")
    
    1.55
    خخ
    1.50
     definitely
    1.47
     will
    1.41
    ↵↵↵
    1.39
     would
    1.38
    Zunanje
    1.31
    !");
    1.27
    Activations Density 0.067%

    No Known Activations