© 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. 75814
    Prev
    Next
    INDEX
    Explanations

    rock and roll

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

    The neuron detects the coordinating conjunction “and” (including variants like “&” or “’n”).

    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
    ﮩ
    -0.90
    etat
    -0.77
     Users
    -0.76
     wahre
    -0.75
    ונה
    -0.75
     deltag
    -0.74
     aš
    -0.73
    Achter
    -0.72
     Và
    -0.72
    Nazionale
    -0.71
    POSITIVE LOGITS
     roll
    0.88
     Roll
    0.85
     Click
    0.82
     mortar
    0.81
    Roll
    0.78
    是因为
    0.75
     fuckin
    0.72
     Accommodations
    0.72
     cargar
    0.71
    })}$
    0.71
    Activations Density 0.018%

    No Known Activations