© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 35027
    Prev
    Next
    INDEX
    Explanations

    potential for, could we

    np_acts-logits-general · gemini-2.5-flash-lite

    Test Procedure: CAN Hypervisor Block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    color
    0.43
    warna
    0.43
    s
    0.43
    THE
    0.40
    .''
    0.40
     fle
    0.38
     vigorously
    0.38
     tosses
    0.38
     Najib
    0.37
    yester
    0.37
    POSITIVE LOGITS
     LOTRAchievement
    0.53
    ㇇
    0.53
     buildFor
    0.49
    aktionen
    0.48
     dangereux
    0.48
    सीएल
    0.47
     magnetization
    0.46
    ซิต
    0.46
     traversal
    0.46
    ዣ
    0.46
    Activations Density 0.000%

    No Known Activations