© 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. 14419
    Prev
    Next
    INDEX
    Explanations

    configuration commands

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

    The neuron fires on content-bearing nouns (i.e. common nouns) rather than on function words.

    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
    izzate
    0.92
    izzata
    0.89
    cypress
    0.83
    unuz
    0.79
     bohater
    0.75
    數位
    0.74
    ă
    0.74
    ците
    0.73
    នៃការ
    0.73
    clouds
    0.72
    POSITIVE LOGITS
    }{:
    0.86
     IRI
    0.82
     ജ
    0.78
     Republican
    0.76
    oría
    0.76
     Orr
    0.75
     Evangelical
    0.74
    </strong>
    0.74
     لص
    0.73
    >)</
    0.73
    Activations Density 0.000%

    No Known Activations