© 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. 20869
    Prev
    Next
    INDEX
    Explanations

    tableau, tabulature, or table listings

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

    The neuron fires on any occurrence of the letter sequence “tabl,” i.e. words or names containing “tabl” (like table, tabla, Tableau, Tablix, таблица, etc.).

    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
    colgante
    -3.02
    schermata
    -2.38
    瞜
    -2.34
    齙
    -2.28
    
    -2.27
    潆
    -2.23
    
    -2.16
    帰る
    -2.13
     unſ
    -2.13
    みよう
    -2.09
    POSITIVE LOGITS
    u
    3.84
    al
    2.91
    <bos>
    2.69
    “
    2.64
    </strong>
    2.56
    ta
    2.56
     the
    2.44
    as
    2.44
    on
    2.36
    un
    2.34
    Activations Density 0.004%

    No Known Activations