© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13745
    Prev
    Next
    INDEX
    Explanations

    harmonic mean

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

    The main thing this neuron does is pick out prominent content-bearing terms—especially key thematic nouns and verbs—in formal or technical prose.

    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
    ახებ
    1.05
     lingering
    0.80
     lain
    0.80
    ധിക
    0.80
     Finances
    0.78
    的信息
    0.77
    爰
    0.77
    ribut
    0.75
    hara
    0.75
     அடையாள
    0.75
    POSITIVE LOGITS
    вся
    0.76
    ☆☆
    0.75
    ます
    0.71
    ный
    0.71
    ين
    0.71
    REVIEW
    0.70
    ер
    0.70
    లా
    0.69
    ير
    0.68
    ROSS
    0.68
    Activations Density 0.000%

    No Known Activations