© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4150
    Prev
    Next
    INDEX
    Explanations

    food ingredients and substances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    י
    0.87
    ا
    0.83
    น
    0.83
    iune
    0.75
    ה
    0.74
    ל
    0.74
    吕
    0.74
    Makanan
    0.72
    lari
    0.70
    த
    0.70
    POSITIVE LOGITS
    .
    0.91
    ong
    0.90
     voltmeter
    0.84
     recebe
    0.80
     micelles
    0.80
     widescreen
    0.80
     didn
    0.79
     willfully
    0.77
    しい
    0.77
    
    0.75
    Activations Density 0.625%

    No Known Activations