© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15517
    Prev
    Next
    INDEX
    Explanations

    alpha contexts

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

    The neuron chiefly detects occurrences of the token “alpha” (in any context or casing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ’
    -3.41
    '
    -3.31
    ’.
    -2.75
    ’-
    -2.70
     ‘
    -2.67
    ’,
    -2.39
      
    -2.30
     ’
    -2.27
    这也
    -2.27
    因为他
    -2.25
    POSITIVE LOGITS
    呖
    3.09
    ൎ
    3.00
     praktis
    2.67
    𓍊
    2.61
    戽
    2.61
    ５
    2.56
    鹟
    2.47
    ization
    2.45
     notre
    2.39
     kreativ
    2.38
    Activations Density 0.021%

    No Known Activations