© 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. 10-GEMMASCOPE-RES-131K
    7. 67987
    Prev
    Next
    INDEX
    Explanations

    words ending in -ist or -ism

    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
     Conseils
    -2.00
     législation
    -1.95
    而后
    -1.95
     &
    -1.88
     sayfa
    -1.84
    重视
    -1.80
    larda
    -1.79
    有著
    -1.76
    ogados
    -1.76
    古风
    -1.72
    POSITIVE LOGITS
    the
    2.05
    3
    1.91
    during
    1.90
    st
    1.89
     своем
    1.87
    9
    1.87
    σουν
    1.86
    ౬
    1.85
     条
    1.84
     schauen
    1.83
    Activations Density 0.051%

    No Known Activations