© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3211
    Prev
    Next
    INDEX
    Explanations

    forum posts and threads

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

    The neuron fires on forum thread header metadata (e.g. “Discussion in ‘Diablo 2 Community Forum’ started by…”).

    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
     moieties
    0.60
    FeO
    0.59
     grantees
    0.59
     roug
    0.58
     monolayers
    0.56
    🏭
    0.56
     coeficiente
    0.55
     ferro
    0.55
     orbitals
    0.54
    ⛴
    0.53
    POSITIVE LOGITS
     thread
    3.06
     Thread
    2.86
    thread
    2.78
     threads
    2.77
    Thread
    2.73
     Threads
    2.42
    线程
    2.41
    threads
    2.38
    THREAD
    2.28
    Threads
    2.25
    Activations Density 0.499%

    No Known Activations