© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10035
    Prev
    Next
    INDEX
    Explanations

    abundance

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

    This neuron detects abstract noun forms—especially quality or state nouns ending in “-ity” (and similar nominalizations).

    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
    imismo
    0.98
    または
    0.88
     లేదా
    0.81
     ಅಥವಾ
    0.81
    หรือ
    0.79
     наших
    0.79
     שלנו
    0.79
    㞱
    0.79
     或者
    0.78
     données
    0.78
    POSITIVE LOGITS
    十足
    0.95
     galore
    0.93
     deutlich
    0.91
    年以上
    0.87
     berupa
    0.82
     بڑا
    0.76
    ครบ
    0.73
    เยอะ
    0.73
    包括
    0.73
    足够
    0.73
    Activations Density 1.394%

    No Known Activations