© 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. 22-GEMMASCOPE-RES-131K
    7. 75034
    Prev
    Next
    INDEX
    Explanations

    your, you, your

    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
     but
    -1.64
     to
    -1.48
     unfortunately
    -1.13
     måste
    -1.08
     principios
    -1.05
     لكن
    -1.04
    但是
    -1.03
     açúcar
    -1.02
     toutefois
    -1.01
    roppo
    -0.98
    POSITIVE LOGITS
     your
    1.67
     you
    1.48
    Your
    1.27
     więc
    1.18
    You
    1.17
    хам
    1.15
     iyong
    1.15
     bandung
    1.14
    your
    1.07
     can
    1.06
    Activations Density 0.016%

    No Known Activations