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. 8506
    Prev
    Next
    INDEX
    Explanations

    m_ prefixes in code

    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
     Erzb
    -0.98
    gulation
    -0.94
     Krzysz
    -0.91
    
    -0.86
     oliveira
    -0.86
    襦
    -0.85
    corbic
    -0.83
    phed
    -0.82
    ufes
    -0.81
     всіх
    -0.81
    POSITIVE LOGITS
    _
    1.64
    _{
    0.92
    \_
    0.90
     p
    0.90
     venezol
    0.82
    illerato
    0.80
     '_'
    0.79
    𝑒
    0.79
    ('')
    0.79
    ograma
    0.79
    Activations Density 0.005%

    No Known Activations