© 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. 115896
    Prev
    Next
    INDEX
    Explanations

    implicit parameters

    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
    lampu
    -0.73
     ziet
    -0.72
    🙎
    -0.71
     geschikt
    -0.71
    crème
    -0.70
    ӷ
    -0.70
    spannung
    -0.68
    THROW
    -0.67
    ▟
    -0.66
    vices
    -0.66
    POSITIVE LOGITS
    implicit
    1.78
     implicit
    1.48
    ()(
    1.40
     Implicit
    1.10
    )(
    1.04
    imab
    1.02
    Implicit
    0.99
    imshow
    0.88
    ascin
    0.86
     boiler
    0.85
    Activations Density 0.015%

    No Known Activations