© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124772
    Prev
    Next
    INDEX
    Explanations

    periodic data, phenomena, extension

    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_10/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
     وأ
    -2.66
     tricked
    -2.64
    <td>
    -2.59
     illustrazione
    -2.58
    ↵↵
    -2.55
     they
    -2.52
     dejected
    -2.52
    𖣘
    -2.50
     singola
    -2.48
    在他的
    -2.45
    POSITIVE LOGITS
    '
    3.31
    ၟ
    2.92
    n
    2.78
    蛩
    2.70
    䊏
    2.63
    咵
    2.50
     ());
    2.50
    
    2.44
    ஂ
    2.44
    帏
    2.41
    Activations Density 0.005%

    No Known Activations