© 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. 28624
    Prev
    Next
    INDEX
    Explanations

    Mr and Ms titles with names

    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
    자인
    -0.89
    🪒
    -0.87
     Originals
    -0.84
     varying
    -0.82
    ونية
    -0.81
    GEAR
    -0.80
    ॠ
    -0.79
     lactation
    -0.78
     šo
    -0.78
    雛
    -0.77
    POSITIVE LOGITS
     Mr
    1.36
    Mr
    1.34
     Ms
    1.08
     said
    1.08
    Ms
    1.08
    corrhi
    1.02
     alegre
    0.99
     manualidades
    0.95
     kilometre
    0.91
     étoient
    0.89
    Activations Density 0.020%

    No Known Activations