© 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. 34-GEMMASCOPE-RES-131K
    7. 62994
    Prev
    Next
    INDEX
    Explanations

    prior to entering

    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
    Приготовление
    -0.84
    甯
    -0.80
    FontOfSize
    -0.78
     član
    -0.76
     gewann
    -0.74
     widerrufen
    -0.72
    Weiter
    -0.70
    윙
    -0.70
    chevêque
    -0.69
    etan
    -0.69
    POSITIVE LOGITS
     entering
    2.92
     entered
    2.88
    Entering
    2.66
     Entering
    2.58
     enter
    2.58
    进入
    2.48
    entering
    2.41
     entry
    2.38
     entrar
    2.23
     enters
    2.19
    Activations Density 0.082%

    No Known Activations