© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105445
    Prev
    Next
    INDEX
    Explanations

    News Detail, SET AL, Midnight Zoo

    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
     tristes
    -1.80
     ส์
    -1.74
    !!)
    -1.58
    渃
    -1.58
     animados
    -1.58
     ибо
    -1.55
     perros
    -1.53
    舠
    -1.52
    !!!)
    -1.50
     editados
    -1.48
    POSITIVE LOGITS
     such
    1.65
    ;
    1.59
    ,
    1.41
    </i>
    1.34
     từ
    1.27
     both
    1.22
     lahko
    1.21
     diverse
    1.20
     today
    1.17
     origin
    1.15
    Activations Density 0.009%

    No Known Activations