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. 127
    Prev
    Next
    INDEX
    Explanations

    image above movie titles

    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
    保证
    -0.86
    naught
    -0.82
     évêque
    -0.79
    颈
    -0.75
    ymo
    -0.74
    <em>
    -0.74
    Hei
    -0.74
     OPC
    -0.74
     legging
    -0.73
     hashing
    -0.73
    POSITIVE LOGITS
     utilized
    0.93
     essentially
    0.92
     tangible
    0.90
     considerably
    0.89
    랍
    0.88
     potentially
    0.87
     possibly
    0.86
     individuals
    0.85
     occasionally
    0.85
     perhaps
    0.84
    Activations Density 0.001%

    No Known Activations