© 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. 42075
    Prev
    Next
    INDEX
    Explanations

    birth dates and ages

    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
    AfterViewInit
    -1.21
     varje
    -1.15
    </b>
    -1.14
     sanitarias
    -1.10
     enkelte
    -1.09
    verbindung
    -1.05
    了他的
    -1.05
     Audit
    -1.05
    XmlElement
    -1.04
     deliciosos
    -1.02
    POSITIVE LOGITS
    ^*)
    1.23
     介绍
    1.12
     タイヤ
    1.02
    mäßigen
    1.01
    ASHINGTON
    0.99
     شوهر
    0.98
     Cæsar
    0.97
     underwent
    0.96
    wery
    0.96
     também
    0.94
    Activations Density 0.107%

    No Known Activations