© 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. 32748
    Prev
    Next
    INDEX
    Explanations

    sequence or subsequent events

    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
     may
    -1.04
     might
    -1.00
     if
    -0.93
    morgen
    -0.88
     information
    -0.85
    `).
    -0.84
    _-
    -0.83
    née
    -0.82
    cents
    -0.82
    tissage
    -0.81
    POSITIVE LOGITS
     afterwards
    1.16
     násled
    1.13
     subsequent
    1.09
     afterward
    1.02
     אחרי
    0.99
     depois
    0.94
     luego
    0.92
     consiguiente
    0.91
     بعد
    0.88
     ensuite
    0.88
    Activations Density 0.013%

    No Known Activations