© 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. 10-GEMMASCOPE-RES-131K
    7. 47620
    Prev
    Next
    INDEX
    Explanations

    places and educational institutions

    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
     inneren
    -1.52
     each
    -1.43
    .”
    -1.43
     that
    -1.39
     what
    -1.38
     eigentlichen
    -1.33
     don
    -1.32
    ஂ
    -1.31
     każdego
    -1.29
     their
    -1.27
    POSITIVE LOGITS
    ']):
    1.43
    cended
    1.40
    laştır
    1.38
    鉏
    1.38
    ']);
    1.33
    weebly
    1.32
    zku
    1.30
    lowed
    1.30
    tired
    1.29
    valuable
    1.28
    Activations Density 0.425%

    No Known Activations