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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 3078
    Prev
    Next
    INDEX
    Explanations

    Gemma, NVIDIA, PostgreSQL, Amelia

    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
    ة
    1.95
     acá
    1.44
    ه
    1.41
    ’
    1.36
    kts
    1.34
    उ
    1.34
     אותו
    1.30
    стояние
    1.30
     längst
    1.30
     sejumlah
    1.29
    POSITIVE LOGITS
    oretically
    1.90
    tedir
    1.63
    ান
    1.55
    ка
    1.52
    teen
    1.49
     is
    1.39
    会有
    1.39
    тся
    1.38
    ై
    1.34
    monary
    1.33
    Activations Density 0.132%

    No Known Activations