© 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. 22-GEMMASCOPE-RES-131K
    7. 38901
    Prev
    Next
    INDEX
    Explanations

    collects, gathers, and manages

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

    The neuron fires strongly on words that name or describe agents/characters by their roles or actions (e.g. “swallows,” “torturer,” “bodyguard,” “detective,” “attorney”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     it
    -1.26
     that
    -1.23
     our
    -1.07
     one
    -0.98
     during
    -0.96
    蘆
    -0.94
     TWO
    -0.94
     or
    -0.93
     शुर
    -0.93
     two
    -0.92
    POSITIVE LOGITS
     himself
    1.48
    himself
    1.27
    很多
    1.17
     každé
    1.16
    いろんな
    1.16
    primarily
    1.09
     peoples
    1.09
    noons
    1.08
     calitate
    1.08
     metoda
    1.07
    Activations Density 0.063%

    No Known Activations