© 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. 98357
    Prev
    Next
    INDEX
    Explanations

    Q: A: Tuesday Prohibition

    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
     sulphide
    -0.71
    ូ
    -0.70
     Tort
    -0.69
     したい
    -0.67
     Dama
    -0.66
     knuckle
    -0.66
    jda
    -0.65
     Fra
    -0.65
    nodeId
    -0.65
     profane
    -0.64
    POSITIVE LOGITS
     family
    1.41
     families
    1.34
    family
    1.27
    Family
    1.23
    Families
    1.21
     FAMILY
    1.20
    families
    1.19
     column
    1.13
     Families
    1.12
     familles
    1.12
    Activations Density 0.014%

    No Known Activations