© 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. 106176
    Prev
    Next
    INDEX
    Explanations

    fi and ic word endings

    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
    icator
    -0.90
     useEffect
    -0.82
     them
    -0.82
     California
    -0.81
    inty
    -0.79
    石垣
    -0.79
     DID
    -0.78
    ety
    -0.77
     VIP
    -0.77
     Colorado
    -0.77
    POSITIVE LOGITS
     and
    0.80
    wörter
    0.80
    értel
    0.80
     função
    0.79
     può
    0.77
    聞き
    0.75
     portrays
    0.75
    __[
    0.74
    Katso
    0.74
    ਾਲ
    0.74
    Activations Density 0.004%

    No Known Activations