© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31706
    Prev
    Next
    INDEX
    Explanations

    models of systems

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

    The neuron fires on the characteristic opening of an academic paper’s abstract (the “Abstract:” heading and its first key content words like “This,” “A,” or similar leading tokens).

    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
     sicherzustellen
    -0.80
    堿
    -0.77
     mulberry
    -0.77
     sweter
    -0.71
     Utilisez
    -0.71
    opes
    -0.71
    ensos
    -0.71
     anfangen
    -0.70
     Ply
    -0.69
     свиде
    -0.69
    POSITIVE LOGITS
     game
    1.02
     model
    0.94
     模型
    0.91
     strategic
    0.90
     two
    0.85
    GameManager
    0.84
    modell
    0.84
     leader
    0.82
    LoginComponent
    0.81
    Completo
    0.81
    Activations Density 0.019%

    No Known Activations