© 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. 128553
    Prev
    Next
    INDEX
    Explanations

    people and individuals

    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
     if
    -1.43
     after
    -1.20
     since
    -1.20
     could
    -1.20
    n
    -1.18
     when
    -1.18
     would
    -1.17
    了些
    -1.17
    b
    -1.16
    0
    -1.13
    POSITIVE LOGITS
     itinéraire
    1.42
    
    1.37
     célè
    1.36
    
    1.34
    𓆏
    1.34
     who
    1.33
     phénom
    1.32
     navigateur
    1.27
     faciliter
    1.27
     frança
    1.26
    Activations Density 0.039%

    No Known Activations