© 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. 4870
    Prev
    Next
    INDEX
    Explanations

    standard, regular, general

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

    The neuron fires on common Latinate qualifying adjectives (e.g. general, respective, ordinary, present, relevant) used to modify nouns.

    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
     einzigen
    0.61
    ()=>{
    0.52
    ième
    0.50
     والتي
    0.50
     प्रतिनिध
    0.49
    様な
    0.49
    ሟ
    0.49
    噉
    0.48
    ร้อง
    0.48
    ]!='
    0.47
    POSITIVE LOGITS
     subclasses
    0.62
     ustaw
    0.55
     عادی
    0.55
     तौर
    0.55
     prejudices
    0.53
     subdivisions
    0.53
     punya
    0.52
    வர்களும்
    0.52
     documentos
    0.52
     autori
    0.52
    Activations Density 0.001%

    No Known Activations