© 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. 12762
    Prev
    Next
    INDEX
    Explanations

    Gonzales, Donovan, Dunkeld, Marianne, Pollard

    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
    とても
    -2.59
    }$
    -2.47
    
    -2.45
    A
    -2.45
    -2.33
     négo
    -2.25
    かなり
    -2.20
    也有
    -2.14
    ak
    -2.09
     vielen
    -2.09
    POSITIVE LOGITS
    铼
    3.53
    掄
    3.00
    酲
    2.97
    甡
    2.88
    赜
    2.80
    玧
    2.69
    祆
    2.61
    疍
    2.58
    軔
    2.56
    各样的
    2.55
    Activations Density 0.038%
    No Known Activations