© 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. 116857
    Prev
    Next
    INDEX
    Explanations

    colors and UI code

    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
    SizeMode
    -0.86
    FirstResponder
    -0.83
    ObjectType
    -0.76
    timeZone
    -0.74
    ३
    -0.73
    MessageOf
    -0.73
    abá
    -0.73
    圭
    -0.73
     mergeFrom
    -0.73
    PrototypeOf
    -0.73
    POSITIVE LOGITS
     hexadecimal
    0.85
     hex
    0.85
     parap
    0.80
     psychological
    0.77
     Hue
    0.75
    یریت
    0.73
    ormous
    0.73
     cependant
    0.73
    Подроб
    0.73
    hade
    0.71
    Activations Density 0.002%

    No Known Activations