© 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. 22-GEMMASCOPE-RES-131K
    7. 10905
    Prev
    Next
    INDEX
    Explanations

    proof or verification

    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
     `
    -2.73
     So
    -2.66
    "
    -2.34
     так
    -2.33
     sassy
    -2.27
     For
    -2.25
     $
    -2.22
     T
    -2.20
    ка
    -2.17
     ?
    -2.16
    POSITIVE LOGITS
    綃
    3.09
     キャンペーン
    3.03
     纹身
    3.02
     墊
    2.86
     花纹
    2.84
    寕
    2.84
     古风
    2.81
     anún
    2.78
     錠
    2.72
    鯪
    2.66
    Activations Density 0.005%

    No Known Activations