© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13834
    Prev
    Next
    INDEX
    Explanations

    SVG DXF formats

    np_acts-logits-general · gemini-2.5-flash-lite

    AMD GPUs and NVIDIA GPUs

    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_31_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
    -
    0.79
    。
    0.64
    ）
    0.59
    -'
    0.55
    '
    0.55
    、
    0.52
    ！
    0.52
    '-
    0.51
    通道
    0.50
    u
    0.48
    POSITIVE LOGITS
     दमदार
    0.65
     மேலும்
    0.58
     वर्कशीट
    0.55
     ஒருங்கிணை
    0.54
    เนื่อง
    0.54
     महत्
    0.53
     વધુ
    0.53
     Comunic
    0.53
     गतिशील
    0.53
     வருகிறது
    0.52
    Activations Density 0.003%

    No Known Activations