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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32645
    Prev
    Next
    INDEX
    Explanations

    securing Internet, Excerpt from

    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
    stm
    -0.69
    ゼロ
    -0.67
    wegen
    -0.67
     unterstützt
    -0.66
    modelos
    -0.66
     suggestive
    -0.65
    素敵
    -0.65
    urea
    -0.65
     aku
    -0.64
    seb
    -0.64
    POSITIVE LOGITS
    幺
    0.78
    ンダント
    0.77
    lottesville
    0.69
     polymorphism
    0.69
    思う
    0.67
    pogon
    0.67
     unanswered
    0.65
     kéo
    0.65
     آمد
    0.65
     которому
    0.65
    Activations Density 0.051%

    No Known Activations