© 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. 10-GEMMASCOPE-RES-131K
    7. 74386
    Prev
    Next
    INDEX
    Explanations

    the word 'In'

    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_10/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
    and
    -2.66
    และ
    -2.53
     și
    -2.48
    鱨
    -2.42
    to
    -2.42
     và
    -2.39
    ising
    -2.38
    st
    -2.28
    le
    -2.22
    W
    -2.20
    POSITIVE LOGITS
    同伴
    2.41
    瞜
    2.36
    伯爵
    2.36
    
    2.28
    ⎆
    2.27
    纮
    2.23
     Of
    2.17
     Terkait
    2.16
    自体は
    2.14
    hadur
    2.11
    Activations Density 0.142%

    No Known Activations