© 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. 34-GEMMASCOPE-RES-131K
    7. 11981
    Prev
    Next
    INDEX
    Explanations

    the concept of "likes"

    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_34/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
    као
    -0.79
    ⎦
    -0.75
    
    -0.75
    ումներ
    -0.75
    GEE
    -0.71
     Kah
    -0.70
     Ebay
    -0.69
    Lep
    -0.69
     Mü
    -0.68
     wä
    -0.68
    POSITIVE LOGITS
     likes
    4.88
    likes
    4.25
     liked
    4.25
     Likes
    3.98
     liking
    3.89
    Likes
    3.88
    liked
    3.23
    LIKE
    3.22
     LIKE
    3.16
    like
    3.13
    Activations Density 0.057%

    No Known Activations