© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 552
    Prev
    Next
    INDEX
    Explanations

    ancient civilizations and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    委员
    1.04
     nCmdShow
    1.00
     المطلوب
    0.98
     அம்மா
    0.98
     KPI
    0.97
     turnkey
    0.97
     KPMG
    0.96
    瘘
    0.94
    入院
    0.92
     агент
    0.91
    POSITIVE LOGITS
     Medieval
    2.58
     medieval
    2.49
     Ancient
    2.44
    Medieval
    2.42
     ancient
    2.32
     antiquity
    2.30
    medieval
    2.27
    Ancient
    2.23
     prehistoric
    2.20
    古代
    2.18
    Activations Density 2.058%

    No Known Activations