© 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. 100943
    Prev
    Next
    INDEX
    Explanations

    matching elements to update

    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
    Configuration
    0.49
    Hints
    0.47
    适应
    0.46
    可以使用
    0.45
    Serialization
    0.44
    练习
    0.44
    构
    0.44
    内存
    0.43
    导
    0.43
    穸
    0.43
    POSITIVE LOGITS
     certain
    0.65
     bestimmte
    0.59
     tertentu
    0.58
     ciertos
    0.57
     bestimmten
    0.55
     values
    0.52
    certain
    0.52
     pagamento
    0.51
     certa
    0.51
     valores
    0.50
    Activations Density 0.077%

    No Known Activations