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. 7862
    Prev
    Next
    INDEX
    Explanations

    words or phrases starting with specific sequences

    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
     kayna
    -0.76
    filename
    -0.73
     használ
    -0.72
     inderdaad
    -0.71
     esencia
    -0.70
     gekenn
    -0.70
     Undo
    -0.69
    だよね
    -0.68
    Harvard
    -0.68
     اللح
    -0.68
    POSITIVE LOGITS
    ringes
    0.94
     breadth
    0.88
     })
    
    0.85
     bucal
    0.82
     komunitas
    0.81
    strator
    0.81
     प्रयोग
    0.81
    🙆
    0.78
     visitors
    0.77
     accessories
    0.77
    Activations Density 0.010%

    No Known Activations