© 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. 13822
    Prev
    Next
    INDEX
    Explanations

    followed by a description

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

    The neuron fires strongly on all‐caps tokens—especially acronyms, initialisms, or other uppercase identifiers.

    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
    etään
    0.94
    үз
    0.86
    entingan
    0.86
     Jeho
    0.85
    ığınız
    0.84
    ätze
    0.84
    ᾷ
    0.84
    ymp
    0.83
     neste
    0.82
     természet
    0.82
    POSITIVE LOGITS
    4
    0.81
    command
    0.80
    coverage
    0.76
    ব
    0.75
    operatorname
    0.73
    crash
    0.73
    6
    0.73
    5
    0.72
    capac
    0.71
    disco
    0.71
    Activations Density 0.000%

    No Known Activations