© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70927
    Prev
    Next
    INDEX
    Explanations

    closing punctuation, then new sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <td>
    -1.77
     :')
    -1.72
    ................
    -1.65
    thentication
    -1.64
    ........
    -1.62
     💖
    -1.59
     😘
    -1.59
    😱
    -1.59
    という
    -1.58
    などを
    -1.57
    POSITIVE LOGITS
     taşlı
    1.97
    籴
    1.84
     inversores
    1.82
    驺
    1.80
    
    1.72
    不就是
    1.71
    轵
    1.70
    はな
    1.70
    んですが
    1.69
    迓
    1.69
    Activations Density 0.044%

    No Known Activations