© 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. 6061
    Prev
    Next
    INDEX
    Explanations

    future events or actions

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

    The neuron detects future‐tense constructions, especially the auxiliary “will” (and related “to be” forms) indicating scheduled or planned events.

    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
    }_{
    0.63
    }
    0.61
     여러
    0.61
     trusted
    0.60
     facilmente
    0.60
    }^{-}
    0.59
     imperme
    0.58
     Bayer
    0.58
     Ihr
    0.57
     transfected
    0.57
    POSITIVE LOGITS
    debut
    0.77
    ເປັນ
    0.77
     είναι
    0.76
    featuring
    0.70
    𝒆
    0.70
     debut
    0.70
     বসে
    0.68
    呈現
    0.66
     centerpiece
    0.66
    是一個
    0.65
    Activations Density 0.027%

    No Known Activations