© 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. 7648
    Prev
    Next
    INDEX
    Explanations

    Authorization determines

    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
    ొప్పి
    0.34
    ！
    0.33
    ឿង
    0.32
    nosť
    0.31
     impactful
    0.31
     пять
    0.30
    拓展
    0.30
    癌
    0.30
     বিশ্ববিদ্যালয়ে
    0.30
     gonorrhea
    0.30
    POSITIVE LOGITS
     ಮಾಹಿತ
    0.34
    hese
    0.33
     questi
    0.32
     Alles
    0.32
     যেহেতু
    0.31
     எல்லா
    0.30
     source
    0.29
     sumber
    0.29
     gleichen
    0.29
     중에서
    0.29
    Activations Density 0.142%

    No Known Activations