© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109530
    Prev
    Next
    INDEX
    Explanations

    section headers like {#sec:1}

    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
     adorable
    -0.85
     pyl
    -0.81
    iri
    -0.78
    brenner
    -0.77
     莉
    -0.76
    的一切
    -0.75
    opinion
    -0.73
     гипер
    -0.72
     XLV
    -0.72
     [...]
    -0.72
    POSITIVE LOGITS
    Trying
    0.98
    Labor
    0.80
     antara
    0.80
    uyên
    0.79
     zimowa
    0.78
    pearing
    0.77
    itom
    0.76
     rojos
    0.76
    ropractor
    0.75
    Fig
    0.75
    Activations Density 0.034%

    No Known Activations