© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 1103
    Prev
    Next
    INDEX
    Explanations

    exclusively by or for

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

    The neuron detects single-word adverbs that signal exclusivity or limitation (e.g. “solely,” “exclusively,” “primarily”).

    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
    特に
    -1.37
     especially
    -1.30
     конкре
    -1.26
     konkret
    -1.25
     semua
    -1.25
    ౬
    -1.21
     exactly
    -1.21
     دقی
    -1.20
    basically
    -1.17
     tutte
    -1.16
    POSITIVE LOGITS
     bedoeld
    1.40
     for
    1.34
     focused
    1.31
     wtedy
    1.30
     лишь
    1.27
     daardoor
    1.20
     daarom
    1.19
     deshalb
    1.17
     devoted
    1.16
     focusing
    1.16
    Activations Density 0.046%

    No Known Activations