© 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. 123503
    Prev
    Next
    INDEX
    Explanations

    large amount of

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

    The neuron fires on phrases that quantify or emphasize large amounts or high magnitudes (e.g., “large amount,” “large quantity,” “large capacity,” etc.).

    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
    糶
    -2.11
    皷
    -2.11
    GEBUR
    -2.08
    ⢪
    -2.06
    瘊
    -2.05
    ჻
    -2.05
    🫃
    -1.88
     Ahnung
    -1.88
     :).
    -1.88
    Ꮷ
    -1.86
    POSITIVE LOGITS
    </strong>
    2.05
     of
    2.02
     If
    1.95
     horrific
    1.90
     (>
    1.89
     не
    1.87
     enormous
    1.85
     помощью
    1.80
     fierce
    1.74
     multifaceted
    1.74
    Activations Density 0.036%

    No Known Activations