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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71397
    Prev
    Next
    INDEX
    Explanations

    out and extended limbs

    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
    ”。
    -1.55
    ！」
    -1.52
    }$
    -1.43
    
    -1.41
    蟆
    -1.41
    ！”
    -1.40
    現在
    -1.38
    。”
    -1.37
    //
    -1.37
     работает
    -1.35
    POSITIVE LOGITS
     for
    1.50
     to
    1.41
    ystemen
    1.39
    
    1.34
    ༑
    1.33
    buttonText
    1.29
    〡
    1.28
    뀨
    1.28
    鉿
    1.28
    \'
    1.25
    Activations Density 0.006%

    No Known Activations