© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13933
    Prev
    Next
    INDEX
    Explanations

    peculiar followed by specific nouns

    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
    ᚔ
    -3.50
    莛
    -3.00
    ༷
    -2.98
    僦
    -2.84
    廰
    -2.77
    桖
    -2.77
    〠
    -2.73
    
    -2.69
    𓁹
    -2.69
    甍
    -2.69
    POSITIVE LOGITS
    '
    3.61
     Also
    3.06
     
    2.92
     That
    2.89
     Because
    2.80
     Trying
    2.75
     Given
    2.53
     There
    2.48
     sizable
    2.48
     lengthy
    2.47
    Activations Density 0.005%

    No Known Activations