© 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. 100160
    Prev
    Next
    INDEX
    Explanations

    public administration

    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
    इटम
    -1.82
    になります
    -1.60
    🪛
    -1.55
     $
    -1.50
    🩹
    -1.44
     https
    -1.41
    がある
    -1.36
    детский
    -1.36
    攆
    -1.34
    ↵
    -1.31
    POSITIVE LOGITS
     that
    1.82
    鱚
    1.64
    鷽
    1.62
    饜
    1.60
     europeo
    1.52
    肄
    1.51
    缡
    1.50
    ꯳
    1.49
     ciep
    1.48
     ᾿
    1.47
    Activations Density 0.521%

    No Known Activations