© 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-16K
    7. 1159
    Prev
    Next
    INDEX
    Explanations

    Sentiment

    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
    3.23
    aa
    3.13
    lardan
    3.13
    u
    3.05
    tól
    2.94
    ar
    2.92
    lng
    2.73
    و
    2.72
    iendo
    2.70
    aan
    2.66
    POSITIVE LOGITS
    써
    1.85
    ভিত্তিক
    1.55
    くちゃ
    1.53
     concomitant
    1.52
    能
    1.52
    로
    1.50
     robe
    1.49
     synthes
    1.48
    ুপ
    1.48
     datas
    1.46
    Activations Density 0.512%

    No Known Activations