© 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. 118699
    Prev
    Next
    INDEX
    Explanations

    names ending in u, i, s, n, y

    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
    tivi
    -0.79
    いわゆる
    -0.75
    いつも
    -0.74
     délicieux
    -0.73
     adapté
    -0.73
    這一
    -0.73
    esimo
    -0.73
     scul
    -0.73
    特斯拉
    -0.73
    áln
    -0.72
    POSITIVE LOGITS
     fisher
    0.77
    鹊
    0.77
    nog
    0.77
    unas
    0.75
    也不
    0.75
     
    0.75
    紧紧
    0.75
    fiés
    0.74
     Fore
    0.73
     }-
    0.73
    Activations Density 0.027%

    No Known Activations