© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 30578
    Prev
    Next
    INDEX
    Explanations

    Soviet Union's role in history

    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
     orientated
    0.44
     rationing
    0.43
    minIndex
    0.43
    紋
    0.42
    ⴳ
    0.41
     offsetX
    0.39
    граф
    0.39
     वापरा
    0.39
    纹
    0.39
     ration
    0.38
    POSITIVE LOGITS
     zdoby
    0.46
     toe
    0.46
     Ahora
    0.44
     zdrav
    0.44
     now
    0.43
     Gesundheit
    0.43
     undeniably
    0.43
     Bo
    0.43
     menschen
    0.43
     health
    0.42
    Activations Density 0.002%

    No Known Activations