© 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. 84761
    Prev
    Next
    INDEX
    Explanations

    common qualifier phrases

    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
    ｌ
    0.54
    essen
    0.51
     hypothes
    0.51
     Scarlett
    0.48
     生命周期函数
    0.47
    orz
    0.46
     于
    0.46
     Copeland
    0.46
    mäßig
    0.45
    ｄ
    0.45
    POSITIVE LOGITS
    ᒧ
    0.43
     HOM
    0.42
     اٹ
    0.41
    惇
    0.41
     تھی
    0.40
     قدیم
    0.40
    一笑
    0.40
    वार्
    0.39
     texts
    0.38
    アウトドア
    0.38
    Activations Density 0.004%

    No Known Activations