© 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. 73496
    Prev
    Next
    INDEX
    Explanations

    why they do

    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
    曽
    -0.88
    巌
    -0.86
     for
    -0.80
     permittee
    -0.79
     Pools
    -0.79
    össe
    -0.79
    IBinder
    -0.77
     nouvelle
    -0.76
     mysqli
    -0.76
    literals
    -0.75
    POSITIVE LOGITS
     hacerlo
    1.01
     did
    0.91
     it
    0.89
     yaptı
    0.85
     today
    0.85
    గు
    0.84
    ឍ
    0.83
    
    0.82
     facilitar
    0.81
     chimie
    0.81
    Activations Density 0.020%

    No Known Activations