© 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. 33193
    Prev
    Next
    INDEX
    Explanations

    reduce total transit ridership

    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
     or
    -1.17
     at
    -1.02
     kanskje
    -0.93
     may
    -0.91
     might
    -0.90
     foolishness
    -0.89
     förra
    -0.88
    uta
    -0.87
     antiquated
    -0.87
     specific
    -0.86
    POSITIVE LOGITS
     violence
    1.03
    actually
    0.98
     tatsächlich
    0.96
     centru
    0.96
     créer
    0.94
    AGGIO
    0.93
     Dinas
    0.93
     bolsos
    0.93
    bici
    0.93
    sanity
    0.91
    Activations Density 0.043%

    No Known Activations