© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 608
    Prev
    Next
    INDEX
    Explanations

    cities, states, countries, months

    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
    っていた
    -1.04
     vaikka
    -1.03
     thậm
    -1.02
    多かった
    -0.99
    ñó
    -0.98
     here
    -0.98
     juega
    -0.97
     jopa
    -0.97
     encontraba
    -0.96
    vlá
    -0.96
    POSITIVE LOGITS
    えると
    0.97
    astu
    0.96
    Код
    0.91
     их
    0.91
     Ensuite
    0.90
     Sociales
    0.90
    要
    0.90
    urlencoded
    0.89
    สินค้า
    0.89
    šo
    0.88
    Activations Density 0.365%

    No Known Activations