© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19771
    Prev
    Next
    INDEX
    Explanations

    names starting with Mik/Mikhail

    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_10/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
     "
    -3.88
     neuen
    -3.34
    ↵↵
    -3.30
     klassischen
    -3.19
     üblichen
    -3.09
     sogenannten
    -2.97
     I
    -2.84
     zahlreichen
    -2.78
    ↵
    -2.70
     offenen
    -2.70
    POSITIVE LOGITS
    齷
    2.88
    檍
    2.86
     reconna
    2.66
     rouges
    2.61
     abus
    2.52
     canzone
    2.50
     makna
    2.48
    哧
    2.47
     probleme
    2.47
     anun
    2.47
    Activations Density 0.003%

    No Known Activations