© 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. 7239
    Prev
    Next
    INDEX
    Explanations

    sax, saxophone, Saxony, Saxena

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

    The neuron strongly activates on any occurrence of the substring “sax” (e.g. in sax, saxon, saxophonist, saxophone).

    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
    寕
    -2.81
    
    -2.45
    ⸫
    -2.41
    型的
    -2.41
     иной
    -2.36
    箩
    -2.33
    ཫ
    -2.33
    งิน
    -2.31
    夘
    -2.28
    ࿊
    -2.28
    POSITIVE LOGITS
    and
    3.50
    A
    2.94
    C
    2.61
     vand
    2.48
    the
    2.47
    鉭
    2.47
     и
    2.44
     και
    2.41
    2
    2.38
    筇
    2.31
    Activations Density 0.002%

    No Known Activations