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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71266
    Prev
    Next
    INDEX
    Explanations

    programming code context

    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
    stroom
    -0.93
     Ê
    -0.91
    を作成
    -0.89
    praxis
    -0.86
     redak
    -0.85
     vrt
    -0.84
     plakat
    -0.82
     kilometr
    -0.82
    allclose
    -0.82
     dokumenta
    -0.82
    POSITIVE LOGITS
     from
    1.19
    Médaille
    0.89
     or
    0.86
     dilaporkan
    0.85
    illermo
    0.85
     nordrhein
    0.84
     kuitenkin
    0.82
    muffin
    0.81
     chết
    0.79
     both
    0.78
    Activations Density 0.013%

    No Known Activations