© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 452
    Prev
    Next
    INDEX
    Explanations

    riddled with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     ofte
    1.98
     ofta
    1.98
    經常
    1.80
     vaak
    1.73
    ,
    1.63
     mnoh
    1.61
    常常
    1.57
    、
    1.54
     organisers
    1.52
    Siempre
    1.51
    POSITIVE LOGITS
     그럼
    1.96
    剩下
    1.93
    那你
    1.93
    셔야
    1.91
    那我
    1.88
    下一步
    1.84
    我现在
    1.79
     이제
    1.78
     Respir
    1.77
    تالي
    1.74
    Activations Density 0.279%

    No Known Activations