© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87235
    Prev
    Next
    INDEX
    Explanations

    names with junior suffixes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     eerste
    -1.42
     ersten
    -1.41
     первые
    -1.33
     первого
    -1.25
     первый
    -1.20
     první
    -1.17
     FIRST
    -1.16
     pierwszy
    -1.16
     first
    -1.13
     primeiro
    -1.10
    POSITIVE LOGITS
     Jr
    3.30
    Jr
    2.25
     jr
    2.16
     second
    2.08
     II
    1.75
     III
    1.71
     junior
    1.69
    jr
    1.56
     Junior
    1.53
     השני
    1.52
    Activations Density 0.008%

    No Known Activations