© 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. 9606
    Prev
    Next
    INDEX
    Explanations

    friends and best friends

    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
     effective
    -0.81
    RUnlock
    -0.81
     at
    -0.81
     конф
    -0.79
    </em>
    -0.79
     clipping
    -0.77
    interceptors
    -0.77
    ورن
    -0.76
    sprechend
    -0.76
    特急
    -0.76
    POSITIVE LOGITS
     friendship
    1.96
     friend
    1.93
     friends
    1.86
    friends
    1.46
    friend
    1.41
    Friend
    1.38
    เพื่อน
    1.38
     buddies
    1.38
    👭
    1.37
     friendships
    1.34
    Activations Density 0.098%

    No Known Activations