© 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. 150974
    Prev
    Next
    INDEX
    Explanations

    from China, Japanese subjects, surety bond, Windows Update

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

    puppygram, needing extreme

    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
    amazon
    0.51
    malloc
    0.49
    requestId
    0.47
    にく
    0.46
    쯜
    0.46
    aggregated
    0.45
    odas
    0.45
    釆
    0.45
     BLUENRG
    0.45
    numberOf
    0.44
    POSITIVE LOGITS
     acestea
    0.55
     acabó
    0.54
     también
    0.52
     tijdens
    0.52
     droga
    0.52
     उद्यान
    0.52
     kon
    0.51
     finisher
    0.51
     pentru
    0.50
     potenci
    0.50
    Activations Density 0.000%

    No Known Activations