© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99504
    Prev
    Next
    INDEX
    Explanations

    balanced and differential signals

    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
    горь
    -0.69
     petite
    -0.66
    bik
    -0.63
    OUG
    -0.63
     MainAxisSize
    -0.61
    bber
    -0.61
    Superview
    -0.61
    Kar
    -0.60
     jud
    -0.60
    bis
    -0.59
    POSITIVE LOGITS
     balanced
    3.27
    balanced
    2.91
    Balanced
    2.86
     Balanced
    2.84
     unbalanced
    2.27
     differential
    2.16
    平衡
    1.98
    differential
    1.92
    Differential
    1.86
     Differential
    1.80
    Activations Density 0.052%

    No Known Activations