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. 8529
    Prev
    Next
    INDEX
    Explanations

    out loud

    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
     out
    -1.48
     Out
    -0.86
    Out
    -0.79
     Sze
    -0.74
    enda
    -0.72
    出了
    -0.70
     OUT
    -0.69
    outre
    -0.69
     участ
    -0.69
    出來
    -0.69
    POSITIVE LOGITS
     loud
    3.63
    loud
    2.73
    Loud
    2.44
     Loud
    2.30
     loudest
    1.81
     гром
    1.74
     louder
    1.73
     LOU
    1.70
     loudly
    1.59
     głoś
    1.48
    Activations Density 0.015%

    No Known Activations