© 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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 2262
    Prev
    Next
    INDEX
    Explanations

    conditional execution and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    Champion
    0.61
    ডেন
    0.57
     Champion
    0.56
    Brass
    0.56
    キ
    0.55
     연구
    0.55
     chaper
    0.55
     отде
    0.54
    チャンピオン
    0.54
    ्रय
    0.54
    POSITIVE LOGITS
    否则
    0.62
    才会
    0.62
     Otherwise
    0.59
     Therefore
    0.56
    ସ୍
    0.56
     במהלך
    0.55
    才
    0.54
    羌
    0.54
    बच्चों
    0.54
    affected
    0.54
    Activations Density 0.100%

    No Known Activations