© 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. 101009
    Prev
    Next
    INDEX
    Explanations

    SEC, Monthly, reflect, ⒎

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

    The neuron strongly activates on the token “reflect,” i.e. it detects occurrences of the word “reflect” (as in code import statements).

    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
     शुर
    -3.30
     That
    -2.73
     achieve
    -2.61
     Some
    -2.58
    ～♪
    -2.48
    </sup>
    -2.48
     provide
    -2.47
    焄
    -2.47
     sparkly
    -2.45
     burgeoning
    -2.45
    POSITIVE LOGITS
     представители
    2.55
    
    2.39
     —
    2.36
     dando
    2.31
    
    2.28
    当下
    2.28
     пять
    2.28
    所有人都
    2.22
    >
    2.19
    🩻
    2.19
    Activations Density 0.000%

    No Known Activations