© 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. 34-GEMMASCOPE-RES-131K
    7. 103392
    Prev
    Next
    INDEX
    Explanations

    media segment delimiters

    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
     cesta
    -1.04
     these
    -1.02
     chalk
    -0.99
     freundlichen
    -0.94
     often
    -0.94
     things
    -0.91
     this
    -0.91
    ?).
    -0.90
    ?),
    -0.90
     erklärte
    -0.90
    POSITIVE LOGITS
    </sup>
    1.00
    ishment
    0.94
     kuning
    0.92
     saks
    0.91
    キング
    0.91
     indicando
    0.89
    Продол
    0.89
    Обу
    0.88
    пенно
    0.87
     seksi
    0.87
    Activations Density 0.005%

    No Known Activations