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. 8067
    Prev
    Next
    INDEX
    Explanations

    birth and death dates

    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
    曜日
    -0.98
     Monarchy
    -0.84
    ByIndex
    -0.83
     VOLTAGE
    -0.82
     voort
    -0.82
    的对象
    -0.79
     downloader
    -0.77
    ག་
    -0.75
    :-)
    -0.74
    👍
    -0.74
    POSITIVE LOGITS
    %;
    
    1.05
     menny
    1.00
    遛
    0.93
    suddenly
    0.92
     loving
    0.90
     "/")
    0.90
     öst
    0.85
     pañ
    0.83
     vs
    0.82
     passed
    0.82
    Activations Density 0.067%

    No Known Activations