© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84643
    Prev
    Next
    INDEX
    Explanations

    events and announcements

    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
    nella
    -1.03
     based
    -0.84
     दौरान
    -0.75
     often
    -0.75
     always
    -0.75
     capable
    -0.74
    してきました
    -0.74
    Passes
    -0.73
     ultima
    -0.72
     ответы
    -0.72
    POSITIVE LOGITS
     announcement
    1.03
     notification
    0.99
    后的
    0.97
     celebration
    0.91
     aldı
    0.91
     accomplished
    0.89
     prácticamente
    0.88
     előtt
    0.86
     monedas
    0.85
    urus
    0.84
    Activations Density 0.004%

    No Known Activations