© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100464
    Prev
    Next
    INDEX
    Explanations

    alcohol toxicity to ill health

    np_acts-logits-general · gemini-2.5-flash-lite

    headings and location markers at the beginning of news articles or documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     it
    -1.67
    re
    -1.37
    </h2>
    -1.28
    </h1>
    -1.27
     F
    -1.21
    するには
    -1.16
     l
    -1.15
     our
    -1.15
     інші
    -1.13
     tratados
    -1.13
    POSITIVE LOGITS
    chées
    1.62
     هار
    1.58
     dinosaurio
    1.53
    endidikan
    1.49
    ()",
    1.48
    相比
    1.46
     rompecabezas
    1.44
     terlaris
    1.41
    赜
    1.40
     perfeitamente
    1.39
    Activations Density 0.002%

    No Known Activations