© 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. 42544
    Prev
    Next
    INDEX
    Explanations

    main + key noun

    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
     and
    -1.78
    bayan
    -1.61
    abilir
    -1.60
     destacado
    -1.55
     всички
    -1.55
    bakter
    -1.55
     abound
    -1.53
     voetballer
    -1.52
     Hinsicht
    -1.52
    ſion
    -1.52
    POSITIVE LOGITS
    re
    2.59
    get
    2.03
    c
    1.90
    at
    1.86
    is
    1.85
    most
    1.84
    no
    1.83
    not
    1.77
    am
    1.73
     he
    1.73
    Activations Density 0.021%

    No Known Activations