© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 798
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to extremely common high‐frequency function words (i.e. stopwords like a, the, to, be, of, and, in, that, etc.).

    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_24_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
    2
    0.93
    1
    0.92
     
    0.89
    0
    0.88
     you
    0.84
    8
    0.84
     two
    0.82
     bạn
    0.82
    3
    0.81
    9
    0.81
    POSITIVE LOGITS
     epistem
    1.20
     ontological
    1.15
     subversive
    1.03
     transcendence
    1.02
     totalitarian
    1.00
     ideological
    0.99
     সার্বভৌম
    0.99
     impover
    0.98
     transcendent
    0.97
     giurid
    0.96
    Activations Density 4.918%

    No Known Activations