© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 15493
    Prev
    Next
    INDEX
    Explanations

    code structure or roles

    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_16k_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
     y
    1.08
     the
    0.98
     which
    0.98
     a
    0.93
    0
    0.90
     this
    0.89
     said
    0.85
     welche
    0.85
    7
    0.84
    6
    0.84
    POSITIVE LOGITS
    LinearLayout
    0.87
    اپنی
    0.87
    ตัน
    0.74
    اف
    0.73
    ன்ஸ்
    0.73
    ústria
    0.72
    逅
    0.72
    ffekt
    0.70
     substandard
    0.69
    Policy
    0.69
    Activations Density 0.139%

    No Known Activations