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. 330
    Prev
    Next
    INDEX
    Explanations

    numbers before award or year

    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
    い
    0.71
    ana
    0.71
    ot
    0.69
     prevención
    0.65
     seguinte
    0.64
    os
    0.64
    做
    0.64
    ình
    0.63
    着
    0.61
    ருக்கு
    0.59
    POSITIVE LOGITS
    ERS
    0.95
    ی
    0.95
    ↵
    0.94
     urges
    0.92
    itu
    0.85
    ים
    0.82
    ല്
    0.82
     affirme
    0.80
    यो
    0.79
    )
    0.79
    Activations Density 0.805%

    No Known Activations