© 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. 23722
    Prev
    Next
    INDEX
    Explanations

    sensors and probes

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

    sensors and optics

    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
     турни
    0.54
    資源
    0.49
     графі
    0.47
    atelier
    0.46
    ար
    0.46
     추진
    0.46
    掲
    0.46
    騁
    0.46
     ресурсы
    0.45
    రుణ
    0.45
    POSITIVE LOGITS
     sensor
    1.27
     sensors
    1.23
     Sensor
    1.13
     sensores
    1.12
    sensor
    1.09
    传感器
    1.05
     Sensors
    1.02
     sensing
    1.01
    sensors
    0.98
    Sensor
    0.97
    Activations Density 0.077%

    No Known Activations