Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 38309
    Prev
    Next
    INDEX
    Explanations

    artificial flavors, additives, preservatives

    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
     Prescription
    0.97
    arı
    0.96
     Prize
    0.93
     HNO
    0.91
    েন
    0.90
    ara
    0.89
    요
    0.88
     Because
    0.87
     Expensive
    0.87
    ง
    0.86
    POSITIVE LOGITS
    тов
    0.90
    യോഗ
    0.88
     différent
    0.87
     tanta
    0.87
    ęs
    0.84
    etable
    0.84
    തിയ
    0.84
    ÉS
    0.82
    étaires
    0.82
     poste
    0.82
    Activations Density 0.007%

    No Known Activations