© 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. 5550
    Prev
    Next
    INDEX
    Explanations

    another question, favorite rage, larger panels

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

    The neuron activates on English quantifier or determiner words that refer to additional or specific quantities (e.g. “another,” “existing,” “more,” “one”).

    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
    érrez
    0.71
    apadani
    0.69
     ው
    0.69
     драмати
    0.69
    <unused0>
    0.68
    သောအ
    0.68
    ibilidades
    0.67
    粙
    0.66
     ኣ
    0.66
    𝗈
    0.66
    POSITIVE LOGITS
     ones
    1.58
    ).
    0.97
     deles
    0.93
     theirs
    0.92
    ものは
    0.91
     Ones
    0.89
     delas
    0.85
    它們
    0.85
     one
    0.82
     serupa
    0.82
    Activations Density 0.387%

    No Known Activations