© 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. 22-GEMMASCOPE-RES-131K
    7. 128069
    Prev
    Next
    INDEX
    Explanations

    leaving or exiting

    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_22/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
     who
    -1.16
     faço
    -1.12
    齟
    -1.02
    ishments
    -0.99
    が付いて
    -0.99
     braço
    -0.96
     chré
    -0.96
     chapéu
    -0.94
    umsy
    -0.93
    OSSARY
    -0.92
    POSITIVE LOGITS
    ató
    0.91
     ola
    0.90
     khỏi
    0.90
     deflation
    0.90
     celib
    0.88
     armas
    0.88
     cramped
    0.87
     کرده
    0.86
     oliva
    0.86
    大家好
    0.86
    Activations Density 0.025%

    No Known Activations