© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 11807
    Prev
    Next
    INDEX
    Explanations

    enumerated lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    Пе
    0.64
    鲔
    0.63
    硖
    0.62
    Tobacco
    0.59
    Benzyl
    0.59
     вас
    0.59
    Sustainability
    0.59
    龈
    0.59
    Copper
    0.58
     Combustion
    0.58
    POSITIVE LOGITS
    :
    0.93
    ,
    0.86
     如果
    0.83
    可以
    0.80
    如果
    0.80
    或者
    0.77
    的
    0.75
    (
    0.74
    选择
    0.74
    用
    0.74
    Activations Density 0.035%

    No Known Activations