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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4341
    Prev
    Next
    INDEX
    Explanations

    sentence endings and new beginnings

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

    contrast and concession

    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_53_width_65k_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
    ⃣
    0.49
     सहित
    0.47
    ️⃣
    0.46
    로부터
    0.45
    持つ
    0.42
    enswert
    0.42
    」、「
    0.42
    ங்களின்
    0.41
    :‏
    0.40
    द्वारे
    0.40
    POSITIVE LOGITS
     although
    0.91
     Although
    0.85
     근데
    0.79
     이는
    0.77
     그런데
    0.76
     ஆனால்
    0.75
     এছাড়া
    0.73
     এছাড়াও
    0.73
     오늘은
    0.72
     এছাড়া
    0.71
    Activations Density 0.712%

    No Known Activations