© 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. 4208
    Prev
    Next
    INDEX
    Explanations

    categories and specific

    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
     Key
    0.55
     Academic
    0.46
     in
    0.46
    s
    0.46
     Sample
    0.45
    ist
    0.43
     lengkap
    0.43
    ear
    0.43
     Fair
    0.43
    O
    0.42
    POSITIVE LOGITS
     spinors
    0.51
    winners
    0.49
    出会
    0.46
    上がる
    0.46
     लक्षात
    0.45
     выигра
    0.45
    ⴽ
    0.45
     upstairs
    0.44
     focuss
    0.44
    рыва
    0.44
    Activations Density 0.022%

    No Known Activations