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. 8386
    Prev
    Next
    INDEX
    Explanations

    ranked, measured percentages, international outlook

    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
     pranks
    -0.91
    inigungs
    -0.79
     meningkat
    -0.75
    屌
    -0.74
     Initially
    -0.73
     drastically
    -0.73
    Atentamente
    -0.73
    了出去
    -0.71
     Defaults
    -0.71
     triliun
    -0.71
    POSITIVE LOGITS
     relative
    0.93
     percentage
    0.91
     measured
    0.90
    measured
    0.88
     scored
    0.87
    どれだけ
    0.87
     VIAF
    0.85
     "%
    0.85
     likely
    0.84
     INDEX
    0.84
    Activations Density 0.030%

    No Known Activations