© 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. 34-GEMMASCOPE-RES-131K
    7. 110521
    Prev
    Next
    INDEX
    Explanations

    Roman and Carthaginian history

    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_34/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
    nię
    -0.77
    앓
    -0.76
    thodoxy
    -0.76
     ALUMIN
    -0.75
     世代
    -0.75
    madol
    -0.75
     Wordle
    -0.74
    isesti
    -0.73
     STM
    -0.73
    sly
    -0.73
    POSITIVE LOGITS
     Roman
    4.28
    Roman
    3.52
     Romans
    3.23
     roman
    2.98
     рим
    2.94
     ROMAN
    2.64
    roman
    2.48
    Romans
    2.47
     romanos
    2.45
    罗马
    2.39
    Activations Density 0.053%

    No Known Activations