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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78157
    Prev
    Next
    INDEX
    Explanations

    mom and dad

    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
    clerView
    -0.94
     vergangenen
    -0.93
     plethora
    -0.91
     intricacies
    -0.90
     Grandmother
    -0.90
     previous
    -0.90
     Betracht
    -0.86
    getPackageName
    -0.86
    getItemId
    -0.85
    aop
    -0.84
    POSITIVE LOGITS
    dad
    1.23
    Dad
    1.23
     Dad
    1.23
     dad
    1.21
     MOM
    1.20
    开发者
    1.19
    Mom
    1.09
     bod
    1.07
     Mom
    1.05
    bod
    1.02
    Activations Density 0.008%

    No Known Activations