© 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. 83208
    Prev
    Next
    INDEX
    Explanations

    classes and workshops

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

    The neuron strongly activates on prepositions that introduce ranges or relationships—especially “for,” “to,” and “from.”

    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
     TEACHING
    -0.93
     CONSTANT
    -0.90
     activit
    -0.89
    ῖς
    -0.85
     Contenido
    -0.85
    PIS
    -0.82
    psycho
    -0.81
    苷
    -0.80
     заявил
    -0.80
    mög
    -0.79
    POSITIVE LOGITS
     beginner
    1.52
     beginners
    1.43
     Intro
    1.42
     introductory
    1.42
     Introduction
    1.38
     adult
    1.34
    Introduction
    1.32
     Thursday
    1.28
     intro
    1.28
     Tuesday
    1.27
    Activations Density 0.030%

    No Known Activations