© 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. 7651
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on “for” when it’s used to introduce a purpose or intended use (e.g. “perfect for a baby quilt,” “room to accommodate your friends,” “designed for smaller areas”).

    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
     KPMG
    0.82
     தெரிவித்த
    0.75
     respectivas
    0.71
     EBITDA
    0.70
    時点で
    0.70
     Deloitte
    0.69
     tujuh
    0.68
    经历
    0.66
     critérios
    0.66
     അന്വേഷ
    0.66
    POSITIVE LOGITS
    用途
    1.63
     用于
    1.37
    用於
    1.34
    用于
    1.31
     используется
    1.31
     사용할
    1.27
     används
    1.26
     kullanılır
    1.26
     použití
    1.24
    Used
    1.23
    Activations Density 3.131%

    No Known Activations