© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102671
    Prev
    Next
    INDEX
    Explanations

    fibro + cell/medical term

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

    text formatting patterns like tilde sequences (~) and technical code syntax elements.

    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
    ﮦ
    -3.30
     capa
    -3.08
    
    -3.03
    s
    -2.97
     enorme
    -2.77
    Of
    -2.75
    6
    -2.75
     {
    -2.72
     kleinere
    -2.64
    1
    -2.64
    POSITIVE LOGITS
    ם
    3.59
    獃
    2.70
    ,))
    2.70
     philosophie
    2.63
    writerow
    2.52
    []
    
    2.50
    +}\
    2.47
     и
    2.47
    })));
    2.45
    奔驰
    2.44
    Activations Density 0.019%

    No Known Activations