© 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. 16185
    Prev
    Next
    INDEX
    Explanations

    hear about or from others

    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
    APOLIS
    -0.94
    ábado
    -0.93
    ৰ
    -0.93
     needing
    -0.90
     vara
    -0.88
     ingles
    -0.86
    statements
    -0.86
    rowser
    -0.85
    udos
    -0.84
    Ń
    -0.84
    POSITIVE LOGITS
     about
    1.71
     from
    1.63
     how
    1.57
     what
    1.35
     why
    1.19
     whether
    1.13
     hornear
    1.06
     that
    1.05
     từ
    1.02
     desecha
    1.02
    Activations Density 0.055%

    No Known Activations