© 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. 9891
    Prev
    Next
    INDEX
    Explanations

    specific professors, courses, research

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

    The neuron strongly activates on multi‐letter uppercase tokens (acronyms/initialisms).

    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
    er
    0.83
    or
    0.80
    as
    0.79
    ter
    0.78
    ucapkan
    0.78
    ah
    0.72
    čí
    0.69
    ।
    0.69
    an
    0.68
    ੀ
    0.66
    POSITIVE LOGITS
    羰
    0.89
    प्लीट
    0.89
    详
    0.88
     produire
    0.85
    基础上
    0.84
    风险
    0.83
    詳
    0.82
    姜
    0.82
     étendue
    0.81
     linéaires
    0.77
    Activations Density 0.000%

    No Known Activations