© 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. 112601
    Prev
    Next
    INDEX
    Explanations

    fire, shame, awareness

    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
     their
    -1.80
     an
    -1.79
     any
    -1.74
     facilitating
    -1.60
     facilitate
    -1.54
     over
    -1.53
     only
    -1.52
     out
    -1.49
     adequate
    -1.49
     Because
    -1.48
    POSITIVE LOGITS
    BASEPATH
    1.50
     DIFFERENT
    1.48
    がこの
    1.45
    僦
    1.45
    Léon
    1.43
    ymo
    1.41
    knows
    1.41
    畾
    1.41
    
    1.41
     verhind
    1.40
    Activations Density 0.075%

    No Known Activations