© 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. 10-GEMMASCOPE-RES-131K
    4. 123831
    Prev
    Next
    INDEX
    Explanations

    shovel and shoving

    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
    as
    -2.86
    at
    -2.86
    ஂ
    -2.84
    舠
    -2.42
    牁
    -2.20
    鉝
    -2.19
    玉石
    -2.13
     FEBR
    -2.13
    i
    -2.08
    鱟
    -2.08
    POSITIVE LOGITS
    妧
    2.28
     "
    2.17
    
    2.16
    女孩子
    2.11
     subray
    2.11
     fundamentals
    2.08
     respald
    2.06
    があれば
    2.05
     είναι
    2.03
     oferec
    2.03
    Activations Density 0.002%

    No Known Activations