© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129321
    Prev
    Next
    INDEX
    Explanations

    Autosomal dominant

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

    Unicode character sequences in technical documents, particularly hexadecimal codes.

    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
     espécies
    -1.31
    』『
    -1.30
    например
    -1.30
    抹茶
    -1.27
     leurs
    -1.23
    <td>
    -1.23
    maları
    -1.22
     bahkan
    -1.20
     лишь
    -1.19
     tým
    -1.19
    POSITIVE LOGITS
    _
    1.49
    ﺅ
    1.45
     a
    1.37
     capucha
    1.36
     nieuw
    1.36
     nuovo
    1.36
    ed
    1.36
    焢
    1.34
     fald
    1.32
    幛
    1.32
    Activations Density 0.035%

    No Known Activations