© 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. 14566
    Prev
    Next
    INDEX
    Explanations

    main branch name

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

    The neuron is most strongly activated by longer, multisyllabic content words (especially nouns and technical terms).

    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
     a
    1.07
     с
    0.95
    is
    0.95
     in
    0.91
     of
    0.89
     an
    0.89
    in
    0.86
     the
    0.85
     as
    0.83
     allá
    0.82
    POSITIVE LOGITS
    」
    1.78
    )
    1.52
    」、
    1.46
    ")
    1.45
    ˮ
    1.42
    ”)
    1.38
    ”،
    1.38
    ')
    1.36
    )،
    1.34
    ）
    1.33
    Activations Density 1.581%

    No Known Activations