© 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. 929
    Prev
    Next
    INDEX
    Explanations

    This neuron responds strongly to celebratory chatter announcing or welcoming “new follower(s)” (e.g. posts exclaiming someone is a new follower).

    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
    elerinin
    0.68
    ogenies
    0.64
    anken
    0.64
    appings
    0.63
    entionally
    0.61
    aryngeal
    0.59
    neutrophiles
    0.58
    爣
    0.58
    alarının
    0.58
    rological
    0.57
    POSITIVE LOGITS
     WWII
    0.67
     privé
    0.65
     NYC
    0.64
     gyda
    0.64
     myös
    0.63
     Esq
    0.63
     nữ
    0.62
     zwei
    0.60
     også
    0.60
     sonst
    0.60
    Activations Density 0.938%

    No Known Activations