© 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. 34-GEMMASCOPE-RES-131K
    7. 1302
    Prev
    Next
    INDEX
    Explanations

    lower geographic or descriptive nouns

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

    The neuron consistently fires on the token “Lower” (or “lower”) when it appears—typically at the start of a multi‐word phrase or hyphenated term (e.g. “Lower-Income,” “lower-limb,” “Lower Salmon River”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    究極
    -0.98
    
    -0.96
    上来
    -0.94
    話が
    -0.94
    Struktur
    -0.90
     غرب
    -0.88
    dijual
    -0.88
    上で
    -0.88
     矢量
    -0.87
    bayern
    -0.86
    POSITIVE LOGITS
     than
    1.65
     Lower
    1.34
    lower
    1.27
    Lower
    1.11
    most
    1.09
     priced
    1.09
     lower
    1.07
     tier
    1.05
    bound
    1.05
     LOWER
    1.04
    Activations Density 0.028%

    No Known Activations