© 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. 40409
    Prev
    Next
    INDEX
    Explanations

    the [word]

    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
    ToMany
    -2.20
    thodoxy
    -2.08
    nosed
    -2.06
    fordshire
    -2.06
    柃
    -2.00
    готовки
    -2.00
    vereignty
    -1.98
    𓐍
    -1.98
    uride
    -1.97
     ไม่
    -1.96
    POSITIVE LOGITS
    “
    2.56
    乃至
    2.33
     things
    2.05
    中国的
    1.98
     bacio
    1.96
    -“
    1.96
     perplexed
    1.94
     этим
    1.88
    ⤿
    1.88
    moteur
    1.87
    Activations Density 0.000%

    No Known Activations