© 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. 50330
    Prev
    Next
    INDEX
    Explanations

    code block endings

    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
     almost
    -1.27
     also
    -1.22
     their
    -1.17
     Almost
    -1.15
     had
    -1.14
     many
    -1.13
     only
    -1.11
     indicated
    -1.11
     various
    -1.09
     ostensibly
    -1.09
    POSITIVE LOGITS
    <eos>
    1.62
     attente
    1.17
    maßnahmen
    1.17
    ↵↵↵↵
    1.16
     méthodes
    1.13
    Kä
    1.09
    möglichkeiten
    1.06
    ↵
    1.06
    以上
    1.05
     şekilde
    1.05
    Activations Density 0.011%

    No Known Activations