© 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. 99690
    Prev
    Next
    INDEX
    Explanations

    variability

    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
    骉
    -2.77
    ⩥
    -2.45
     Extensive
    -2.44
    
    -2.36
     lakukan
    -2.36
    箆
    -2.34
    訕
    -2.33
    蹌
    -2.28
    揠
    -2.28
     формы
    -2.27
    POSITIVE LOGITS
     "
    3.56
    栳
    2.86
    蛧
    2.66
    _
    2.64
     This
    2.39
    s
    2.31
     dieser
    2.31
    .'
    2.25
     dieses
    2.25
     ("
    2.22
    Activations Density 0.005%

    No Known Activations