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. 8523
    Prev
    Next
    INDEX
    Explanations

    aviators and aviation

    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
    Commonwealth
    -0.74
    Dots
    -0.73
    hms
    -0.73
    dots
    -0.72
     Esther
    -0.70
     Commonwealth
    -0.69
    urus
    -0.69
    verein
    -0.69
    ζ
    -0.69
     JUN
    -0.67
    POSITIVE LOGITS
    ation
    0.92
    ATION
    0.84
    ator
    0.74
    tion
    0.73
    ionic
    0.71
     Shoulder
    0.71
    ators
    0.71
    setzung
    0.70
     mediation
    0.69
    ication
    0.68
    Activations Density 0.040%

    No Known Activations