© 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. 25849
    Prev
    Next
    INDEX
    Explanations

    interconnected and interdependent

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

    The neuron detects phrases describing multiple elements (e.g. factors, components, species) that interact with one another.

    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
    两种
    -1.03
    二人
    -0.93
    院校
    -0.92
    𝐱
    -0.89
    这两个
    -0.88
    ontaneous
    -0.84
     kesk
    -0.84
    mpotent
    -0.84
     Differenz
    -0.84
    timacy
    -0.82
    POSITIVE LOGITS
     interrelated
    2.72
     interconnected
    2.67
     interdependent
    2.31
     взаимо
    2.25
    相互
    2.14
     interact
    2.14
     interdependence
    2.14
    互相
    2.00
     interacting
    1.99
     interplay
    1.95
    Activations Density 0.090%

    No Known Activations