© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7819
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on section or heading titles—tokens that introduce or label distinct document sections.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    K
    0.84
    Bundes
    0.77
    Films
    0.77
    H
    0.77
    S
    0.74
    শেষে
    0.73
     scrive
    0.72
    HAM
    0.71
    Regions
    0.71
    Allium
    0.71
    POSITIVE LOGITS
    हली
    0.73
    𝒏
    0.65
     intercepted
    0.64
     לי
    0.62
     আজকে
    0.61
     हेव
    0.61
    ഷേധ
    0.61
     cranking
    0.61
     डॉलर
    0.60
     وصول
    0.60
    Activations Density 0.000%

    No Known Activations