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. 84
    Prev
    Next
    INDEX
    Explanations

    documentation structure and keywords

    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
     },
    
    -0.84
    ënten
    -0.84
     nieve
    -0.83
     برانيه
    -0.82
     estime
    -0.81
     masculin
    -0.81
    ার্
    -0.80
    alay
    -0.78
    enscha
    -0.78
     afric
    -0.78
    POSITIVE LOGITS
    </h2>
    3.13
    <h2>
    1.88
    </h1>
    1.57
    </h3>
    1.52
    </h5>
    1.50
    "){
    1.36
    ")){
    1.28
    </h4>
    1.26
    </blockquote>
    1.23
    </h6>
    1.23
    Activations Density 0.010%

    No Known Activations