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. 8120
    Prev
    Next
    INDEX
    Explanations

    timestamps and version numbers

    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
    a
    -1.05
     milioni
    -0.96
    soort
    -0.93
    each
    -0.91
    so
    -0.91
    ob
    -0.90
     bArr
    -0.89
    `
    -0.89
     प्रोडक्ट
    -0.87
    w
    -0.87
    POSITIVE LOGITS
    Lma
    1.19
    蹺
    1.14
    classy
    1.05
    moments
    1.03
    一秒
    1.01
    fluffy
    1.00
     seconds
    0.98
    jedno
    0.97
    bouncy
    0.96
    bumper
    0.96
    Activations Density 0.009%

    No Known Activations