© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 48226
    Prev
    Next
    INDEX
    Explanations

    convection, ceasefire, detection, cracking, addiction

    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_65k_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
    嫩
    0.43
    數
    0.41
    illar
    0.41
    ্দ
    0.40
     pizz
    0.40
    ként
    0.40
     ενεργ
    0.40
     πολ
    0.39
    opi
    0.38
    慑
    0.38
    POSITIVE LOGITS
    자에
    0.49
    available
    0.46
     Tbilisi
    0.45
     статистики
    0.44
    Rights
    0.44
    Available
    0.44
    Opportunities
    0.43
    ania
    0.43
    AVAILABLE
    0.43
    ‚
    0.43
    Activations Density 0.013%

    No Known Activations