© 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. 99511
    Prev
    Next
    INDEX
    Explanations

    .

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

    This neuron fires on the “X is a Y” definitional pattern in article intros—i.e. the copular “is a” sentences that introduce and define an entity.

    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
     over
    -0.88
     like
    -0.82
     starts
    -0.81
    ritos
    -0.78
     побе
    -0.77
     group
    -0.75
     punti
    -0.73
     but
    -0.71
     comes
    -0.70
     nearly
    -0.70
    POSITIVE LOGITS
    Ill
    0.95
     stadig
    0.84
    →
    0.82
    opha
    0.81
    tamaan
    0.81
     onChange
    0.80
    zauber
    0.79
    ய்ய
    0.78
    Market
    0.77
    polator
    0.76
    Activations Density 0.003%

    No Known Activations