© 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. 111646
    Prev
    Next
    INDEX
    Explanations

    attribute assignments

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

    numeric height values in code, particularly in XML and CSS layout specifications.

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

    The neuron fires on standalone numeric literals containing a decimal point (i.e. floating-point numbers).

    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
     また
    -2.02
    냑
    -1.84
     эффектив
    -1.79
    u
    -1.75
    a
    -1.72
     员
    -1.71
    ";
    -1.70
    轼
    -1.67
    ᠂
    -1.66
    apuram
    -1.66
    POSITIVE LOGITS
     essentials
    1.98
     a
    1.95
    是很
    1.84
     You
    1.84
    ABBRE
    1.80
     of
    1.74
     řekl
    1.71
    を使用した
    1.71
     allgeme
    1.70
    趼
    1.70
    Activations Density 0.023%

    No Known Activations