© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12886
    Prev
    Next
    INDEX
    Explanations

    Steven Kahn: knowledge

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

    The neuron strongly activates on tokens that are part of academic citation metadata—author names, initials, and related reference elements.

    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
     추진
    0.68
     océ
    0.66
     fermionic
    0.66
     decouple
    0.65
    úblic
    0.65
    㜌
    0.64
    constrained
    0.63
     корпуса
    0.63
    犠
    0.63
     esemplari
    0.62
    POSITIVE LOGITS
     pathophys
    1.32
     COPD
    1.21
     pathophysiology
    1.20
     Clinical
    1.17
     clinically
    1.13
     Gastroenter
    1.13
     clinical
    1.09
     gastroenter
    1.07
     psoriasis
    1.05
    Clinical
    1.04
    Activations Density 0.314%

    No Known Activations