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. 8106
    Prev
    Next
    INDEX
    Explanations

    note, followed by characteristics

    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
    throated
    -0.79
    шит
    -0.78
     lille
    -0.76
     Kini
    -0.74
     sexto
    -0.73
    приятия
    -0.71
    腩
    -0.71
    ritter
    -0.69
     uren
    -0.69
    英語
    -0.68
    POSITIVE LOGITS
    Note
    3.22
     Note
    3.05
     note
    3.03
    note
    2.48
     notes
    2.44
    Notes
    2.42
    NOTE
    2.38
     NOTE
    2.38
     Notes
    2.20
    NOTES
    1.81
    Activations Density 0.014%

    No Known Activations