© 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. 1793
    Prev
    Next
    INDEX
    Explanations

    greek letter alpha followed by hyphen

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

    The neuron fires on instances of the Greek letter “α” (alpha) in the text.

    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
     a
    -3.52
    h
    -2.95
    <bos>
    -2.70
    ↵↵
    -2.67
    o
    -2.66
    ing
    -2.64
    }
    -2.63
    »
    -2.47
      
    -2.47
    ]
    -2.41
    POSITIVE LOGITS
    蕺
    3.44
     indiquer
    2.84
     bluz
    2.59
    脔
    2.58
     這
    2.58
    ᮣ
    2.48
     intrigue
    2.45
    ization
    2.45
     mogli
    2.42
    Ꮏ
    2.42
    Activations Density 0.004%

    No Known Activations