© 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. 52572
    Prev
    Next
    INDEX
    Explanations

    computer viruses, support, techs

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

    computers and related concepts

    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
    ק
    0.92
     atentos
    0.83
    ،
    0.82
    ق
    0.80
    یم
    0.75
    قا
    0.75
    ین
    0.74
    وع
    0.74
    سک
    0.74
     críticas
    0.71
    POSITIVE LOGITS
     computer
    1.12
     computers
    1.00
     Computers
    0.98
    computer
    0.97
     komputer
    0.97
     Computer
    0.95
    Computer
    0.93
     컴퓨터
    0.93
     कंप्यूटर
    0.93
     компью
    0.90
    Activations Density 0.040%

    No Known Activations