© 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. 22-GEMMASCOPE-RES-131K
    7. 127896
    Prev
    Next
    INDEX
    Explanations

    financial success or control

    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
    Negative Logits
     you
    -2.44
    ansvar
    -1.95
    がありますが
    -1.93
     personnalisées
    -1.77
     vendredi
    -1.72
     today
    -1.68
     offrent
    -1.62
     ratón
    -1.61
     estrenar
    -1.59
     vždy
    -1.58
    POSITIVE LOGITS
     had
    1.95
     would
    1.71
     was
    1.61
    之事
    1.55
     by
    1.55
    民众
    1.55
    之王
    1.42
     his
    1.41
     правительства
    1.41
     could
    1.35
    Activations Density 0.023%

    No Known Activations