© 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. 11132
    Prev
    Next
    INDEX
    Explanations

    listing specific columns

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

    This neuron detects idiomatic expressions or clichés that describe steady improvement or growth over time (e.g. “gone from strength to strength”).

    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
     lidt
    0.58
    ↵↵↵↵↵
    0.54
    里面
    0.50
    ﺮ
    0.49
    <start_of_image>
    0.47
     maaf
    0.47
    ↵↵↵↵
    0.47
     mittel
    0.46
    พันธ์
    0.46
     继续访问
    0.44
    POSITIVE LOGITS
    idega
    0.58
    ichel
    0.55
    oraus
    0.53
    signOut
    0.53
    。“
    0.52
    ático
    0.52
    éi
    0.52
     Attractive
    0.52
    	
    0.52
    
    0.52
    Activations Density 0.098%

    No Known Activations