© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34677
    Prev
    Next
    INDEX
    Explanations

    tanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⠘
    -0.71
     アイス
    -0.71
    谨
    -0.70
    ומי
    -0.69
    ſto
    -0.69
    cussion
    -0.68
     Мария
    -0.68
    anghai
    -0.67
    电池
    -0.66
    TestData
    -0.66
    POSITIVE LOGITS
     tanks
    4.22
     tank
    4.09
    Tank
    3.08
    tank
    3.06
     Tanks
    2.98
     Tank
    2.92
    tanks
    2.61
    Tanks
    2.59
     TANK
    2.55
    TANK
    2.38
    Activations Density 0.038%

    No Known Activations