© 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. 120533
    Prev
    Next
    INDEX
    Explanations

    User Agent MUST

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

    webkit and browser technologies

    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
     bottlene
    0.55
    므
    0.54
    ⵙ
    0.50
     выгляд
    0.50
    اً
    0.49
    드릴
    0.48
    🐟
    0.48
    ငံ
    0.47
    ार
    0.46
    감
    0.45
    POSITIVE LOGITS
     eroded
    0.46
     parthen
    0.46
     oxidized
    0.44
     elongated
    0.44
     cleaved
    0.44
     epicenter
    0.43
     HOPE
    0.43
    郊
    0.43
     gradients
    0.42
     sympathy
    0.42
    Activations Density 0.000%

    No Known Activations