© 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. 59706
    Prev
    Next
    INDEX
    Explanations

    scientific analyses

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

    scientific text using the word "analyses" particularly in research papers and academic studies.

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

    The neuron selectively fires on the plural noun “analyses.”

    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
    नलोड
    -3.13
    嫱
    -2.69
    unjungi
    -2.61
    蚡
    -2.58
    ୪
    -2.55
    鈇
    -2.55
    鼍
    -2.44
    ?
    -2.41
     algun
    -2.36
    媗
    -2.33
    POSITIVE LOGITS
    踽
    2.83
    没有
    2.53
    釹
    2.52
    ia
    2.50
    to
    2.39
    饜
    2.36
    vantaged
    2.33
    al
    2.22
    ſu
    2.16
    
    2.14
    Activations Density 0.008%

    No Known Activations