© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34690
    Prev
    Next
    INDEX
    Explanations

    your or you, future possibility

    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
     was
    -1.27
     now
    -1.16
     می‌توان
    -1.10
     ofrecemos
    -1.09
    让我
    -1.07
     today
    -1.07
     あります
    -1.05
     fatale
    -1.05
     my
    -1.04
     myself
    -0.99
    POSITIVE LOGITS
     your
    4.56
     you
    3.73
     will
    2.83
     yourself
    2.20
     youll
    1.98
    あなたの
    1.89
     आपको
    1.87
     вас
    1.83
     budete
    1.82
     خواهید
    1.81
    Activations Density 0.031%

    No Known Activations