© 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. 103550
    Prev
    Next
    INDEX
    Explanations

    possessive 's contraction

    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
    ひた
    -1.84
    いえば
    -1.80
    擰
    -1.66
     timmar
    -1.63
    葙
    -1.63
    opheles
    -1.62
    笵
    -1.60
     flota
    -1.59
    chenta
    -1.58
     impec
    -1.55
    POSITIVE LOGITS
     and
    2.05
     to
    2.03
    ’
    1.93
    та
    1.80
     Also
    1.60
     There
    1.59
     Get
    1.55
    𝐲
    1.53
     ‘‘
    1.53
     Although
    1.53
    Activations Density 0.048%

    No Known Activations