© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49019
    Prev
    Next
    INDEX
    Explanations

    words before specific continuations

    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
    LElement
    -0.80
     obraz
    -0.79
    onymus
    -0.76
     المعد
    -0.73
    Whilst
    -0.71
    iint
    -0.71
    texture
    -0.71
     correlated
    -0.70
    кай
    -0.70
     comuniques
    -0.69
    POSITIVE LOGITS
    声道
    0.78
     Fren
    0.78
     hài
    0.77
    ("*");
    0.75
     Theodore
    0.74
     pectin
    0.74
    ifax
    0.70
    uru
    0.70
     excited
    0.69
    ܐ
    0.69
    Activations Density 0.085%

    No Known Activations