© 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. 13911
    Prev
    Next
    INDEX
    Explanations

    funds with

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

    The neuron strongly fires on short, all‐caps tokens (two to four letters) such as street‐type abbreviations (ST, PL), time zones (CDT, BST), years, and other uppercase acronyms.

    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
    𝘨
    0.93
    гат
    0.92
    BleStatus
    0.91
    밂
    0.89
     그래도
    0.88
    𝘬
    0.86
     даже
    0.84
    వర
    0.83
     иска
    0.83
    𝘧
    0.83
    POSITIVE LOGITS
    t
    0.81
    </i>
    0.75
    تع
    0.74
    s
    0.72
    tive
    0.68
     Govt
    0.65
    0.65
     Alvin
    0.64
     Government
    0.64
    től
    0.64
    Activations Density 0.000%

    No Known Activations