© 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. 4134
    Prev
    Next
    INDEX
    Explanations

    chronological order

    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
    ا
    2.59
    基づ
    2.02
     Confira
    2.02
     malnourished
    1.95
    י
    1.95
     vieja
    1.88
     khusus
    1.85
     eléctrico
    1.85
     laboral
    1.78
     sido
    1.77
    POSITIVE LOGITS
    т
    2.13
    ت
    2.08
    it
    2.02
    SN
    1.74
    THE
    1.67
    ivity
    1.65
    melody
    1.59
    PO
    1.59
    с
    1.57
            
    1.56
    Activations Density 0.002%

    No Known Activations