© 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. 22-GEMMASCOPE-RES-131K
    7. 68331
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and characters

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

    The neuron flags numeric literals (including decimal numbers, octal/hex constants, and other numeric tokens).

    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
    N
    -2.17
    P
    -1.90
     M
    -1.82
    A
    -1.81
    B
    -1.80
    V
    -1.79
    X
    -1.78
    M
    -1.77
    R
    -1.77
     S
    -1.77
    POSITIVE LOGITS
     Inſ
    1.70
    🫃
    1.68
    Zdrav
    1.66
    
    1.63
    鷽
    1.63
    骉
    1.61
    鹩
    1.60
     唯美
    1.60
    karena
    1.59
    Gön
    1.59
    Activations Density 0.046%

    No Known Activations