© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12470
    Prev
    Next
    INDEX
    Explanations

    biomass, contemporáneo, Pythagorean, comprehension

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

    The neuron selectively fires on uncommon proper‐noun tokens (like specific place names or chemical compound names).

    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_31_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
    pronged
    0.34
     phụ
    0.32
    
    0.32
     Karna
    0.32
    Ϟ
    0.32
    Eloquent
    0.32
     Dapat
    0.32
     kttt
    0.31
    
    0.31
    )`
    0.31
    POSITIVE LOGITS
    iversity
    0.38
    ight
    0.35
     School
    0.35
    ittle
    0.35
    ack
    0.34
     school
    0.34
    ick
    0.34
    idge
    0.34
    uart
    0.34
    ieu
    0.34
    Activations Density 0.286%

    No Known Activations