© 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-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-65K
    7. 1226
    Prev
    Next
    INDEX
    Explanations

    model

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ioutil
    0.69
     সিঁ
    0.53
     digitalWrite
    0.52
    鞑
    0.52
     शत्र
    0.48
     ক্যারি
    0.47
     peces
    0.46
     />';
    0.46
    ¯</
    0.46
    ंदर
    0.45
    POSITIVE LOGITS
     models
    2.22
     model
    2.09
    模型
    1.97
     모델
    1.96
    モデル
    1.95
     Models
    1.95
     модели
    1.93
     modelos
    1.91
     моделей
    1.86
    模型的
    1.85
    Activations Density 1.837%

    No Known Activations