© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11070
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on words and phrases used to state personal opinions or judgments (e.g., “I think,” “means,” “credible enough,” “don’t … think,” 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
    linkedin
    0.80
    报警
    0.78
     činjen
    0.78
    咨询
    0.76
    监测
    0.69
    協助
    0.67
    睃
    0.66
    安全
    0.66
    验
    0.66
    अमेरिकी
    0.65
    POSITIVE LOGITS
     fanbase
    1.09
     Goku
    1.03
     gameplay
    0.92
     underwhelming
    0.90
     devs
    0.89
     Vegeta
    0.89
     MSRP
    0.85
     Anime
    0.84
     Tets
    0.84
     Sasuke
    0.82
    Activations Density 0.072%

    No Known Activations