© 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. 34-GEMMASCOPE-RES-131K
    7. 106214
    Prev
    Next
    INDEX
    Explanations

    advice and support for citizens

    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
    Negative Logits
     HIER
    -0.76
    IFICATIONS
    -0.75
    ises
    -0.75
    保有
    -0.74
    ั
    -0.73
    ón
    -0.73
    ALF
    -0.73
     spiegel
    -0.73
    ➳
    -0.72
    ibatkan
    -0.71
    POSITIVE LOGITS
     advice
    1.24
     Samar
    1.13
     Advice
    1.11
     Citizens
    1.07
     advise
    1.05
    advice
    1.00
     support
    0.95
     advisor
    0.93
    Citizens
    0.91
     advisors
    0.86
    Activations Density 0.030%

    No Known Activations