© 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. 34-GEMMASCOPE-RES-131K
    7. 90245
    Prev
    Next
    INDEX
    Explanations

    attending school classes

    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_34/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
    âge
    -0.84
     Partai
    -0.79
    unitas
    -0.77
     Leningrad
    -0.75
    atol
    -0.74
    Ikus
    -0.72
    Beschreibung
    -0.71
    થ
    -0.68
    を作
    -0.68
     estuaries
    -0.68
    POSITIVE LOGITS
     classes
    6.09
    classes
    4.53
     Classes
    4.25
    Classes
    4.16
     CLASSES
    3.47
     clases
    3.31
    CLASSES
    3.27
     class
    3.23
     classe
    2.66
     courses
    2.47
    Activations Density 0.055%

    No Known Activations