© 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. 32409
    Prev
    Next
    INDEX
    Explanations

    low functional property

    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
     misunderstood
    -0.81
    ]-\
    -0.79
    |+\
    -0.78
    ᵇ
    -0.75
     escritora
    -0.75
    الحي
    -0.75
     Crazy
    -0.74
    umin
    -0.74
     arquitect
    -0.73
     آخر
    -0.73
    POSITIVE LOGITS
    只能
    1.03
    far
    0.89
    reve
    0.84
    Far
    0.84
     Betracht
    0.82
     barely
    0.82
    weak
    0.82
     Sequo
    0.81
    Weak
    0.80
    顯
    0.80
    Activations Density 0.005%

    No Known Activations