© 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. 72840
    Prev
    Next
    INDEX
    Explanations

    Roman numeral VIII

    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
    注意事
    -2.81
    神
    -2.75
    
    -2.67
     mauva
    -2.66
    曏
    -2.59
     نداره
    -2.55
     wich
    -2.55
     become
    -2.50
    湏
    -2.48
    ？！”
    -2.44
    POSITIVE LOGITS
     If
    2.67
     selben
    2.55
     This
    2.55
    2
    2.52
    4
    2.38
    わから
    2.28
    With
    2.25
     With
    2.23
     '
    2.16
    9
    2.14
    Activations Density 0.004%

    No Known Activations