© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14836
    Prev
    Next
    INDEX
    Explanations

    Structured data with numbers and labels

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

    The neuron reliably lights up on concrete product or asset nouns—names of items or downloadable media (e.g. “Resume,” “background,” “wireless device,” “packaging,” “printing,” 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
    A
    0.68
    R
    0.66
    ﯿ
    0.62
    ﻨ
    0.61
     R
    0.59
    Sens
    0.59
    T
    0.59
    De
    0.59
    C
    0.59
    Ν
    0.59
    POSITIVE LOGITS
    গণের
    0.61
     または
    0.60
     allError
    0.60
     whatsoever
    0.56
     objString
    0.56
     newfound
    0.56
     ওরফে
    0.56
    সকল
    0.55
     anymore
    0.55
     сведения
    0.55
    Activations Density 0.367%

    No Known Activations