© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105174
    Prev
    Next
    INDEX
    Explanations

    contrasting choices

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

    This neuron activates strongly on the comparative phrase “rather than,” signaling instances of contrastive comparison.

    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
     लेकिन
    -1.38
     or
    -1.34
     vagy
    -1.31
     know
    -1.28
    ri
    -1.26
     d
    -1.23
    不仅
    -1.21
     bądź
    -1.20
     not
    -1.18
     it
    -1.16
    POSITIVE LOGITS
    licite
    1.40
    bkz
    1.40
    ITERATURE
    1.38
    ጺ
    1.36
     of
    1.35
     delito
    1.34
    ดอก
    1.34
     πριν
    1.33
    ⡱
    1.33
    ﹅
    1.32
    Activations Density 0.031%

    No Known Activations