© 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. 22-GEMMASCOPE-RES-131K
    7. 25531
    Prev
    Next
    INDEX
    Explanations

    Email, The, Effect, 1

    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
     two
    -1.53
     this
    -1.31
     all
    -1.27
     it
    -1.25
     get
    -1.22
     three
    -1.21
     six
    -1.20
    Like
    -1.20
     several
    -1.20
     impressive
    -1.16
    POSITIVE LOGITS
     trám
    1.60
    
    1.31
    
    1.27
     花纹
    1.27
    uristic
    1.23
     cérebro
    1.23
    Estos
    1.22
    皤
    1.22
     tyto
    1.21
     バッジ
    1.20
    Activations Density 0.010%

    No Known Activations