© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139121
    Prev
    Next
    INDEX
    Explanations

    harmful or exploitative content

    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_262k_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
    ACE
    0.48
    2
    0.44
     sería
    0.41
    1
    0.41
     García
    0.40
    顛
    0.40
     মা
    0.40
    descriptor
    0.40
    AGE
    0.39
     कलेक्टर
    0.39
    POSITIVE LOGITS
    参数向量
    0.48
    üyor
    0.48
    嚧
    0.46
     menghubungi
    0.45
    ikar
    0.43
    KeepOriginal
    0.43
    必须要
    0.42
    别人
    0.42
    ყენ
    0.42
    ı
    0.42
    Activations Density 0.006%

    No Known Activations