© 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. 116029
    Prev
    Next
    INDEX
    Explanations

    connection or disconnection

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

    This neuron activates on occurrences of the word “connect” (and its variants such as “connecting,” “CONNECTING,” or “connect(…)”) in the text.

    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
    ism
    -0.93
    ist
    -0.89
    𝓶
    -0.82
    ality
    -0.81
    isEnabled
    -0.81
    デス
    -0.80
    ell
    -0.80
    ill
    -0.79
    imer
    -0.75
    ain
    -0.75
    POSITIVE LOGITS
     Connect
    0.88
     sicura
    0.85
    濟
    0.84
    uyucu
    0.84
     soffer
    0.84
     with
    0.81
    érc
    0.80
     dichi
    0.80
    院校
    0.80
    cion
    0.79
    Activations Density 0.023%

    No Known Activations