© 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. 91235
    Prev
    Next
    INDEX
    Explanations

    XML tags, codes, or identifiers

    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
    投
    -0.82
    潍
    -0.79
    provin
    -0.79
    parker
    -0.79
    jme
    -0.77
     veran
    -0.77
     szob
    -0.77
    тони
    -0.76
    gsub
    -0.75
    cass
    -0.75
    POSITIVE LOGITS
    밝
    0.82
     anbieten
    0.81
     BYU
    0.81
     عربي
    0.78
    sender
    0.78
    Conclusie
    0.76
     doubtless
    0.76
     Occidental
    0.76
     notably
    0.75
    IES
    0.74
    Activations Density 0.007%

    No Known Activations