© 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. 75433
    Prev
    Next
    INDEX
    Explanations

    attorney general

    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
    縢
    -1.93
    ୩
    -1.84
    änden
    -1.84
     что
    -1.84
    غی
    -1.83
     Unternehmer
    -1.80
    TintMode
    -1.80
    v
    -1.77
     harrowing
    -1.77
     -
    -1.77
    POSITIVE LOGITS
    ↵
    2.19
     メニュー
    1.97
     to
    1.95
     of
    1.95
     fhall
    1.81
    橚
    1.77
     Obr
    1.73
    >"+
    1.73
     なん
    1.70
     técn
    1.66
    Activations Density 0.016%

    No Known Activations