© 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. 1853
    Prev
    Next
    INDEX
    Explanations

    exclusive: or // created by

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

    This neuron marks tokens appearing in the main “body” section—i.e. after the initial header/intro—activating strongly on any word once the document shifts into its detailed content.

    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
     Olivier
    -0.93
     robot
    -0.88
     Hover
    -0.79
    うわ
    -0.78
     Robot
    -0.77
    opropyl
    -0.75
    🛡
    -0.74
     Kay
    -0.74
    omorph
    -0.73
     Uno
    -0.72
    POSITIVE LOGITS
     plane
    1.05
    plane
    0.98
     tools
    0.92
     PLANE
    0.89
    tote
    0.87
     planes
    0.85
     Stuhl
    0.84
    outils
    0.83
     japan
    0.81
     apprenticeship
    0.81
    Activations Density 0.012%

    No Known Activations