© 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. 104632
    Prev
    Next
    INDEX
    Explanations

    furthering progress or understanding

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

    This neuron detects occurrences of the word “further” (including its inflected forms furthering, furthered, 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
    ࣭
    -1.79
    延伸閱讀
    -1.73
     教室
    -1.70
    厲害
    -1.66
     »)
    -1.64
     tenté
    -1.63
    leopard
    -1.61
    釙
    -1.60
     recompensa
    -1.60
     obligado
    -1.59
    POSITIVE LOGITS
    ’
    2.67
     $
    2.03
    f
    2.02
    s
    1.96
     $\
    1.95
    x
    1.91
     “
    1.90
    k
    1.90
    ”
    1.89
    ‘
    1.89
    Activations Density 0.015%

    No Known Activations