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. 8414
    Prev
    Next
    INDEX
    Explanations

    well succeeded, well used, well learned

    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
     not
    -0.90
     even
    -0.77
    pthread
    -0.75
    Basil
    -0.75
    ish
    -0.73
    ʲ
    -0.72
    otypic
    -0.72
     historia
    -0.72
     Sergio
    -0.72
     freund
    -0.71
    POSITIVE LOGITS
    veillance
    1.28
    heure
    0.98
     墓
    0.95
     خاصی
    0.91
     буенча
    0.91
     Beschluss
    0.90
     peggio
    0.88
     LXX
    0.87
     puțin
    0.85
    ఫ
    0.84
    Activations Density 0.007%

    No Known Activations