© 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. 9315
    Prev
    Next
    INDEX
    Explanations

    blouse, xlsx, porosity, hydroxide, Targeted

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

    file extensions and technical terminology related to document formats, especially ".xlsx" Excel files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to occurrences of the word “blouse.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    1
    -3.98
    7
    -3.02
    2
    -2.84
    </b>
    -2.70
    that
    -2.69
    </i>
    -2.64
    5
    -2.63
    </td>
    -2.63
    <td>
    -2.50
    8
    -2.45
    POSITIVE LOGITS
    
    3.03
    鞑
    2.72
    最后由
    2.56
    诶
    2.45
    節約
    2.41
    みたいです
    2.38
    ですかね
    2.38
    驺
    2.36
    驀
    2.36
    性价比
    2.31
    Activations Density 0.004%

    No Known Activations