© 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. 55836
    Prev
    Next
    INDEX
    Explanations

    names and places preceding 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
     products
    -0.82
    EMS
    -0.76
    ʃ
    -0.73
     điệu
    -0.72
     diary
    -0.71
     dựng
    -0.71
    products
    -0.70
     Gest
    -0.69
     estimates
    -0.66
    mau
    -0.66
    POSITIVE LOGITS
     Lyra
    1.16
     Pullman
    1.10
    viez
    0.81
     Madeleine
    0.81
    MRS
    0.80
     Coulter
    0.80
    懣
    0.79
     trilogy
    0.78
    ąż
    0.78
    imel
    0.77
    Activations Density 0.013%

    No Known Activations