© 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. 34-GEMMASCOPE-RES-131K
    7. 344
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and locations

    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_34/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
    Marca
    -0.78
     Bonne
    -0.72
    Muff
    -0.68
    PROTOCOL
    -0.67
     inserts
    -0.66
    jaz
    -0.66
     Straus
    -0.66
    Chy
    -0.66
    Mailer
    -0.66
     unum
    -0.66
    POSITIVE LOGITS
    ัติ
    0.83
     Wire
    0.82
     Peanut
    0.77
    cuterie
    0.77
    Wire
    0.77
    Etiquetas
    0.76
     wire
    0.75
     Alabama
    0.75
    //-----
    0.73
     Ozark
    0.73
    Activations Density 0.036%

    No Known Activations