© 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. 113953
    Prev
    Next
    INDEX
    Explanations

    in love with

    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
     to
    -1.98
    are
    -1.86
    was
    -1.73
    er
    -1.72
    ons
    -1.71
    <bos>
    -1.71
     которого
    -1.68
    S
    -1.68
     trasera
    -1.66
    et
    -1.65
    POSITIVE LOGITS
     envio
    1.79
     别墅
    1.70
     through
    1.68
     trocar
    1.67
     romero
    1.63
     粥
    1.61
     llor
    1.59
     aeron
    1.59
     знаю
    1.57
    tividade
    1.55
    Activations Density 0.002%

    No Known Activations