© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3206
    Prev
    Next
    INDEX
    Explanations

    reciprocal social interaction and interests

    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
    াত
    -0.73
     PRC
    -0.73
    WGS
    -0.68
    InStock
    -0.67
     CTRL
    -0.66
     Exams
    -0.66
    Gaia
    -0.66
    宁
    -0.64
     META
    -0.64
     coupler
    -0.64
    POSITIVE LOGITS
    zhu
    0.71
    lus
    0.69
    隷
    0.67
    elashes
    0.66
    listen
    0.65
     أوروبا
    0.65
     prowadzi
    0.63
    redor
    0.63
    Notifier
    0.63
    atise
    0.63
    Activations Density 0.130%

    No Known Activations