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-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 316
    Prev
    Next
    INDEX
    Explanations

    installation, sampling device, counselor, dialect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    از
    0.59
    زا
    0.58
    اسي
    0.55
    用
    0.55
    有
    0.54
    在
    0.53
    高
    0.52
    管
    0.52
    利率
    0.52
    等待
    0.52
    POSITIVE LOGITS
     बहुमत
    0.65
     आवंट
    0.64
     श्रीलंका
    0.57
    OW
    0.57
    Ii
    0.57
    ν
    0.57
     証明
    0.57
    OG
    0.56
     स्तंभ
    0.55
    OSS
    0.55
    Activations Density 0.001%

    No Known Activations