© 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. 104933
    Prev
    Next
    INDEX
    Explanations

    words starting with Multi

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

    The neuron fires on occurrences of the substring “multi” (e.g. the “Multi-” or “multi” prefix in words).

    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
    ↵↵
    -3.66
     
    -3.44
     dando
    -3.06
     contando
    -3.06
     generando
    -3.00
     provocando
    -2.89
      
    -2.84
     langen
    -2.56
     creando
    -2.56
    凄く
    -2.52
    POSITIVE LOGITS
    ၞ
    3.06
    膛
    2.92
     démocr
    2.92
    ஂ
    2.91
    .....
    2.88
    畵
    2.86
    ו
    2.84
    .......
    2.83
    呜呜
    2.80
    ጺ
    2.80
    Activations Density 0.056%

    No Known Activations