© 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. 82906
    Prev
    Next
    INDEX
    Explanations

    ad-sounding words

    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
    oluted
    -0.88
    ^{[
    -0.83
     erhält
    -0.81
    dul
    -0.77
    WITHOUT
    -0.77
    Acquired
    -0.77
     stalo
    -0.76
    mote
    -0.75
    uced
    -0.75
    cran
    -0.72
    POSITIVE LOGITS
    ্দ
    0.91
     руке
    0.82
    nalités
    0.82
    </code>
    0.80
    Но
    0.78
    Ад
    0.77
    题
    0.76
    Глава
    0.74
    所属
    0.74
    Под
    0.74
    Activations Density 0.056%

    No Known Activations