© 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. 34-GEMMASCOPE-RES-131K
    7. 55660
    Prev
    Next
    INDEX
    Explanations

    other and sides

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

    The neuron strongly activates on occurrences of the word “Other” (in any case or as part of identifiers) in titles, headings, or 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_34/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
    likle
    -0.92
     نیست
    -0.86
     Ungarn
    -0.86
     tenido
    -0.85
     социальной
    -0.84
    いかない
    -0.82
    コマ
    -0.81
    īgi
    -0.80
    Nx
    -0.79
     fibrosis
    -0.77
    POSITIVE LOGITS
    worldly
    1.98
     than
    1.86
     peoples
    1.37
    word
    1.29
    ness
    1.27
     Half
    1.24
    人的
    1.15
    side
    1.14
     niż
    1.12
    than
    1.05
    Activations Density 0.021%

    No Known Activations