© 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. 10-GEMMASCOPE-RES-131K
    7. 128067
    Prev
    Next
    INDEX
    Explanations

    aged with numerical ranges

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

    The neuron detects explicit age specifications, i.e. occurrences of “aged” (or similar) followed by a numeric age.

    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
    felpa
    -3.00
    涐
    -2.94
    チュラル
    -2.91
    ჻
    -2.88
    鱘
    -2.88
    
    -2.84
     撮っ
    -2.78
     controladores
    -2.72
    嗵
    -2.72
    篳
    -2.64
    POSITIVE LOGITS
    2
    4.47
    of
    4.16
    if
    3.34
    4
    3.33
    7
    3.25
    ir
    3.16
    3
    3.13
    9
    3.09
    5
    3.08
    ol
    3.05
    Activations Density 0.006%

    No Known Activations