© 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. 33423
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, or listings

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

    advanced AI tools

    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
    ↵
    0.52
    에
    0.51
    사
    0.43
    용
    0.43
     enigmatic
    0.43
    ں
    0.43
    ද
    0.42
     maestros
    0.42
    ם
    0.42
     shar
    0.41
    POSITIVE LOGITS
     имуще
    0.58
     可愛
    0.56
     就是
    0.54
     时尚
    0.53
     डिप्लोमा
    0.52
    ান
    0.52
    bac
    0.51
    财产
    0.51
     可以
    0.51
     Optimization
    0.49
    Activations Density 0.000%

    No Known Activations