© 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-262K
    7. 143247
    Prev
    Next
    INDEX
    Explanations

    Lunar eclipses

    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
    শা
    0.44
     সৃষ্টি
    0.41
    創作
    0.38
    navigationItem
    0.38
    뀔
    0.37
    ാള
    0.37
     Marino
    0.37
    込
    0.37
     Cara
    0.36
     PCI
    0.36
    POSITIVE LOGITS
    త్స
    0.52
     தமிழரசுக்
    0.52
     الجرس
    0.51
     aprend
    0.50
    đer
    0.48
     लिए
    0.47
     चित्रों
    0.47
     disinformation
    0.47
    forms
    0.46
    èles
    0.46
    Activations Density 0.000%

    No Known Activations