© 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. 123776
    Prev
    Next
    INDEX
    Explanations

    Dale, names, locations

    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
     they
    -3.11
    栳
    -3.09
    
    -2.78
    i
    -2.64
    窳
    -2.61
    section
    -2.52
    籥
    -2.47
     Можно
    -2.44
    see
    -2.41
     Если
    -2.41
    POSITIVE LOGITS
    т
    2.47
    沨
    2.42
                    
    2.28
    ᠁
    2.28
    媜
    2.25
    耵
    2.22
    F
    2.20
     mereka
    2.17
     одежда
    2.16
    ная
    2.14
    Activations Density 0.004%

    No Known Activations