© 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. 154261
    Prev
    Next
    INDEX
    Explanations

    order, service, or enter

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

    incredibly compromised or promising

    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
    构建
    0.50
    o
    0.42
    模拟
    0.42
    实现
    0.41
     xây
    0.40
     펼
    0.40
    起こ
    0.40
     networks
    0.40
    র্বর
    0.39
    ্য
    0.39
    POSITIVE LOGITS
    Thro
    0.55
    <unused535>
    0.55
     antigua
    0.55
     Sog
    0.52
     czę
    0.52
     Marbella
    0.51
    ISTA
    0.51
     Roder
    0.50
     Sonia
    0.49
    JSPA
    0.49
    Activations Density 0.001%

    No Known Activations