© 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. 109876
    Prev
    Next
    INDEX
    Explanations

    castle and chateau names

    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
     nunca
    -0.91
     Zel
    -0.85
    DateTimeFormat
    -0.77
     distancing
    -0.76
     equili
    -0.75
    摯
    -0.72
     correspondent
    -0.72
    šla
    -0.71
    いずれ
    -0.70
    的文章
    -0.70
    POSITIVE LOGITS
    worry
    0.75
     rotina
    0.75
     newUser
    0.74
    ➜
    0.69
    pageCount
    0.69
    濃い
    0.69
    facility
    0.68
     grà
    0.68
    solicited
    0.67
    𝜙
    0.67
    Activations Density 0.024%

    No Known Activations