© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64846
    Prev
    Next
    INDEX
    Explanations

    locations, people, or groups

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

    This neuron detects tokens that are part of the main movie synopsis or plot summary section of a description.

    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
     often
    -0.96
     September
    -0.90
     zawier
    -0.89
     incredible
    -0.85
     gyvento
    -0.83
     this
    -0.83
    뇨
    -0.81
     Clips
    -0.80
    !
    -0.80
    icolo
    -0.79
    POSITIVE LOGITS
    bodyParser
    1.09
     accedere
    1.01
     titular
    0.98
    ByteBuffer
    0.96
    komt
    0.93
     endforeach
    0.91
     directora
    0.91
     ),
    0.91
    >)</
    0.90
    )}\
    0.90
    Activations Density 0.059%

    No Known Activations