© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70077
    Prev
    Next
    INDEX
    Explanations

    various prefixes

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

    The neuron is triggered by two‐letter sequences of uppercase letters (e.g. “Li”, “Ol”, “En”, “Co”).

    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
    ⮜
    -2.81
    ⢅
    -2.59
    
    -2.41
    
    -2.31
    狴
    -2.28
    驺
    -2.16
    罴
    -2.16
    ↑↑↑</
    -2.09
    اوم
    -2.06
    ᕱ
    -2.06
    POSITIVE LOGITS
    >
    3.56
    2
    3.44
    3
    3.33
    9
    3.16
    I
    3.02
    This
    2.94
    1
    2.94
    It
    2.91
    ,”
    2.88
    ’
    2.86
    Activations Density 0.041%

    No Known Activations