© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85117
    Prev
    Next
    INDEX
    Explanations

    theta and META contexts

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

    The neuron fires on occurrences of the Greek letter name “Theta” (e.g. in mathematical notation or model‐space names).

    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
     titolata
    -2.84
     was
    -2.84
    棡
    -2.81
    镠
    -2.69
     красота
    -2.58
    嚶
    -2.55
     طويلة
    -2.52
     nadru
    -2.52
    𞤢
    -2.52
    ệc
    -2.45
    POSITIVE LOGITS
     "
    3.44
    Depending
    2.72
    It
    2.66
    4
    2.56
    There
    2.55
    Which
    2.53
    A
    2.52
    ''
    2.48
    ного
    2.47
    7
    2.44
    Activations Density 0.001%

    No Known Activations