© 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. 50535
    Prev
    Next
    INDEX
    Explanations

    puppy, breed, history

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

    philosophical struggle, biblical narrative, potential trend

    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
    í
    0.47
    ingt
    0.45
    p
    0.45
    ash
    0.45
     Democratic
    0.44
    infested
    0.43
    mass
    0.42
    tha
    0.41
    dang
    0.41
     जश्न
    0.41
    POSITIVE LOGITS
     eax
    0.53
     ایپل
    0.53
    电池
    0.52
     chargingStation
    0.52
     ബാറ്ററി
    0.51
    架构
    0.50
    钚
    0.49
    传感器
    0.48
    "。
    0.48
     syslog
    0.48
    Activations Density 0.000%

    No Known Activations