© 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. 1183
    Prev
    Next
    INDEX
    Explanations

    advances in technologies

    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
     if
    -1.78
    fromUtf
    -1.68
    子を
    -1.66
    老祖
    -1.50
    toPromise
    -1.46
     Dennoch
    -1.44
    信念
    -1.41
    咳
    -1.41
    <bos>
    -1.40
    стойчи
    -1.40
    POSITIVE LOGITS
    ↵↵
    2.03
    4
    1.86
     soste
    1.80
     technologies
    1.78
     advancements
    1.66
     tasca
    1.63
     minore
    1.59
     entsprechende
    1.56
    </h4>
    1.56
    ほん
    1.55
    Activations Density 0.072%

    No Known Activations