© 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. 22-GEMMASCOPE-RES-131K
    7. 34342
    Prev
    Next
    INDEX
    Explanations

    order numbers and references

    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
     and
    -1.24
     деца
    -1.03
    ₅
    -1.01
     religieux
    -1.01
     prêmio
    -1.00
    知道
    -0.98
     блюдо
    -0.97
    etr
    -0.93
     παιδιά
    -0.93
     çalışmalar
    -0.93
    POSITIVE LOGITS
     felicitación
    1.15
    ربای
    1.13
    VILL
    1.09
     timestamp
    1.08
    ┈
    1.04
    şağı
    1.04
     Satellites
    1.03
    믈
    1.02
    ynie
    1.02
     kunjungan
    1.02
    Activations Density 0.011%

    No Known Activations