© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12198
    Prev
    Next
    INDEX
    Explanations

    This neuron detects tokens characteristic of user‐generated blog or forum comment text—greetings, pleas, blessings, and other conversational or spam‐like 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_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
    überkü
    0.76
     lesiones
    0.75
    ش
    0.73
     conseils
    0.70
     helemaal
    0.70
    eline
    0.69
     comprend
    0.69
     danno
    0.69
    啪
    0.68
     personnelles
    0.68
    POSITIVE LOGITS
     sahaja
    0.83
    society
    0.79
    s
    0.79
     Caucasus
    0.79
     Rhine
    0.79
     mula
    0.77
     Khark
    0.77
     сына
    0.76
    Hx
    0.76
     Cyprus
    0.76
    Activations Density 0.001%

    No Known Activations