© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70778
    Prev
    Next
    INDEX
    Explanations

    angle, trigonometry, mathematics

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

    The neuron activates on occurrences of the word “angle,” especially when used in referring to a measured or calculated angle.

    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
    Not
    -2.45
    Here
    -2.30
    c
    -2.27
    Now
    -2.22
    One
    -2.20
    An
    -2.20
    If
    -2.19
    Any
    -2.16
     It
    -2.09
    It
    -2.09
    POSITIVE LOGITS
    ientras
    2.23
    
    1.90
    炻
    1.81
     that
    1.79
    𐬹
    1.77
     museos
    1.73
    潾
    1.73
    珰
    1.72
    ↵
    1.70
    嗩
    1.70
    Activations Density 0.001%

    No Known Activations