© 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. 67524
    Prev
    Next
    INDEX
    Explanations

    fragmented world, society, chromatin

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

    The neuron detects forms of the word "fragment" and concepts related to fragmentation or division.

    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
     sfondo
    -1.78
     fatta
    -1.77
    躋
    -1.77
     ordini
    -1.74
     orari
    -1.73
    ;
    -1.73
     portata
    -1.73
     that
    -1.56
    分明
    -1.56
    事も
    -1.53
    POSITIVE LOGITS
     $
    2.00
    </h4>
    1.83
     \&
    1.77
    \_
    1.77
    </em>
    1.68
    现有
    1.68
    \_\_
    1.65
    \&
    1.63
     \_
    1.57
     $*
    1.55
    Activations Density 0.044%

    No Known Activations