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. 106
    Prev
    Next
    INDEX
    Explanations

    mat/meth/math beginnings

    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
    cenia
    -0.82
     Locking
    -0.79
    Thread
    -0.76
    PLUGIN
    -0.75
    parseLong
    -0.74
    iale
    -0.73
     hjemmeside
    -0.73
     casting
    -0.73
    톤
    -0.72
     boreal
    -0.71
    POSITIVE LOGITS
    ชน
    0.85
    matically
    0.77
    ☉
    0.76
    яр
    0.75
    Cassandra
    0.71
     města
    0.69
     Kirke
    0.68
     môžu
    0.68
     stří
    0.68
     Accept
    0.67
    Activations Density 0.030%

    No Known Activations