© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    each other / one another

    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
     всеми
    -1.37
     segala
    -1.28
     wszel
    -1.27
    所有的
    -1.20
     모든
    -1.18
     همه
    -1.16
     mọi
    -1.16
     todas
    -1.13
     sowohl
    -1.10
     todos
    -1.09
    POSITIVE LOGITS
     each
    9.25
    Each
    6.06
    each
    5.66
     Each
    5.22
     eachother
    5.03
     fiecare
    3.91
     chacun
    3.91
     EACH
    3.89
     chaque
    3.78
    EACH
    3.77
    Activations Density 0.130%

    No Known Activations