© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25534
    Prev
    Next
    INDEX
    Explanations

    methods of interaction

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

    The neuron flags relatively formal, content-bearing words (e.g. “through,” “continued,” “political”) that serve as discourse connectors or topic markers.

    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
     concerns
    -0.94
     perkembangan
    -0.92
    
    -0.88
    aments
    -0.88
    parseDouble
    -0.87
    اصيل
    -0.86
    ním
    -0.86
    tehen
    -0.86
    ůvod
    -0.86
    fica
    -0.85
    POSITIVE LOGITS
     brute
    1.45
     appeal
    1.27
     persuasion
    1.26
     through
    1.24
     dialogue
    1.19
     force
    1.18
     resort
    1.17
     carrot
    1.15
     diálogo
    1.13
     diplomacy
    1.10
    Activations Density 0.050%

    No Known Activations