© 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. 11059
    Prev
    Next
    INDEX
    Explanations

    "I have" + past actions

    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
    0
    -2.92
    -
    -2.84
     that
    -2.83
    :
    -2.58
    A
    -2.58
    7
    -2.50
    ↵↵
    -2.30
    6
    -2.27
    8
    -2.22
           
    -2.13
    POSITIVE LOGITS
     ").
    2.73
    ᯅ
    2.53
    麈
    2.41
    閦
    2.33
    馓
    2.31
     obvio
    2.28
    ︐
    2.28
    
    2.27
     murale
    2.27
    !")
    2.27
    Activations Density 0.032%

    No Known Activations