© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6660
    Prev
    Next
    INDEX
    Explanations

    friends and associates

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects mentions of personal friendships—words and phrases referring to “friend” or “friends.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
     Ähn
    -1.54
     jährlich
    -1.54
    igreja
    -1.49
     interface
    -1.44
    Bagaimana
    -1.44
     passenden
    -1.40
     aktuellen
    -1.40
     Häufig
    -1.38
     bienestar
    -1.38
     möglicherweise
    -1.37
    POSITIVE LOGITS
     and
    3.20
     cordones
    1.38
    stood
    1.34
     whofe
    1.31
    tifications
    1.30
     Cancelar
    1.29
     liet
    1.27
    vriende
    1.27
    rà
    1.25
    {`
    1.25
    Activations Density 0.019%

    No Known Activations