© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54490
    Prev
    Next
    INDEX
    Explanations

    Stardust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يكية
    0.58
    Massachusetts
    0.53
    ሳሌ
    0.50
     currentLocation
    0.48
    Collection
    0.48
    Мы
    0.48
    Artifact
    0.48
    λ
    0.48
    Virus
    0.47
    戙
    0.47
    POSITIVE LOGITS
    workbench
    0.45
    dise
    0.45
     triggers
    0.44
     intuitive
    0.44
     superior
    0.44
     எழு
    0.43
     meteor
    0.42
    monitoring
    0.42
    meteor
    0.42
     intuitively
    0.41
    Activations Density 0.002%

    No Known Activations