Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8565
    Prev
    Next
    INDEX
    Explanations

    financial analysts or reports

    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
    unton
    -0.77
     campagnes
    -0.76
    }%
    
    -0.75
    Handled
    -0.73
    
    -0.69
    Phaser
    -0.68
     Napa
    -0.68
    號
    -0.68
     chairs
    -0.67
     Meld
    -0.67
    POSITIVE LOGITS
     analyst
    1.57
     analysts
    1.57
     RBC
    1.51
     UBS
    1.41
     Goldman
    1.41
     Jeffer
    1.39
     Bernstein
    1.35
     Citi
    1.35
     Morgan
    1.31
     Macquarie
    1.23
    Activations Density 0.043%

    No Known Activations