© 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. 22-GEMMASCOPE-RES-131K
    7. 9489
    Prev
    Next
    INDEX
    Explanations

    parents and children

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ว์
    -0.97
     سوال
    -0.88
    each
    -0.87
     Forecasts
    -0.85
    ❖
    -0.79
     getTarget
    -0.79
    ńska
    -0.78
    Ours
    -0.77
    $
    -0.75
     Recipients
    -0.75
    POSITIVE LOGITS
     children
    1.45
     kids
    1.16
     child
    1.16
    Figli
    1.13
     Sahne
    1.10
    Children
    1.08
    bisoft
    0.97
     Jeden
    0.97
     childcare
    0.95
     NUCLEAR
    0.95
    Activations Density 0.083%

    No Known Activations