© 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. 10386
    Prev
    Next
    INDEX
    Explanations

    css width and height

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

    semicolons in CSS style declarations within HTML and code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on the semicolon delimiters in inline CSS style attributes.

    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
    ter
    -1.76
    Чтобы
    -1.74
    嵓
    -1.73
    硨
    -1.65
    戋
    -1.65
    皷
    -1.64
    will
    -1.63
    N
    -1.56
    ner
    -1.54
    #%%
    -1.54
    POSITIVE LOGITS
     and
    2.06
    ERTY
    1.67
     with
    1.65
     otros
    1.63
    yatı
    1.60
     in
    1.58
     Bezeichnung
    1.54
     Bedienung
    1.53
     Mehrheit
    1.52
     or
    1.51
    Activations Density 0.021%

    No Known Activations