© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12425
    Prev
    Next
    INDEX
    Explanations

    ensuring positive outcomes

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

    The neuron activates on the collocation “sure to” (the word “sure” followed by “to”).

    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
     Nye
    0.69
    他人
    0.68
     cik
    0.67
     McD
    0.66
     Cummins
    0.66
     fabrik
    0.65
     supabase
    0.64
    蝿
    0.64
     Avis
    0.64
     Marley
    0.64
    POSITIVE LOGITS
    Sure
    0.89
     Sure
    0.84
     SURE
    0.82
    sure
    0.80
     garantiza
    0.80
     sure
    0.75
     Segurança
    0.73
    ỡng
    0.73
     certeza
    0.72
     chắc
    0.71
    Activations Density 0.192%

    No Known Activations