© 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. 110934
    Prev
    Next
    INDEX
    Explanations

    names and specific topics

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

    The neuron is highly tuned to spotting the Ember Data “belongsTo” relationship keyword in code.

    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
     {
    -3.48
    ᵴ
    -2.86
    ーーーー
    -2.75
    廋
    -2.58
    i
    -2.45
    ي
    -2.39
    In
    -2.34
     funcionales
    -2.33
     Leuten
    -2.30
     программа
    -2.27
    POSITIVE LOGITS
     Also
    2.86
     Then
    2.52
    "
    2.48
    vantaged
    2.34
    leqslant
    2.30
     )
    2.30
     —
    2.17
    which
    2.16
    佇
    2.14
     Only
    2.11
    Activations Density 0.000%

    No Known Activations