© 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. 8967
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively fires on technical terms, acronyms, and section‐style headings—i.e. title-case or all-caps tokens and numbered labels.

    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
    ed
    0.98
    U
    0.85
    R
    0.81
    C
    0.80
    N
    0.79
    Spawn
    0.79
    M
    0.76
    ṃ
    0.76
    MPI
    0.75
    arası
    0.75
    POSITIVE LOGITS
     pengukuran
    0.94
     rearranging
    0.90
    <unused2199>
    0.90
     pembahasan
    0.85
     plaisir
    0.84
     photometry
    0.84
     adjusting
    0.84
    ெமி
    0.84
     изменение
    0.83
     berhubungan
    0.83
    Activations Density 20.982%

    No Known Activations