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. 661
    Prev
    Next
    INDEX
    Explanations

    Blisk browser for web developers

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

    comet tails

    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
     to
    1.15
     was
    1.03
    н
    0.98
     at
    0.91
     be
    0.91
    ă
    0.90
     for
    0.89
    기
    0.84
     do
    0.80
    <0x0D>
    0.78
    POSITIVE LOGITS
    ning
    0.61
    lıkla
    0.61
    数が
    0.59
    вається
    0.58
     인해
    0.55
    lycer
    0.54
    daar
    0.54
    rumah
    0.52
     диапа
    0.52
    ุ
    0.52
    Activations Density 1.947%

    No Known Activations