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

    Neuronpedia

    Jacobian LensNEW
    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. 15460
    Prev
    Next
    INDEX
    Explanations

    Describing what happens next

    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
    nics
    0.48
    ্ব
    0.47
    gcf
    0.45
    pch
    0.44
     Uch
    0.44
    é
    0.44
    γον
    0.43
     Ung
    0.42
     adolescents
    0.42
     Plastic
    0.42
    POSITIVE LOGITS
     fruitful
    0.45
    ຕ
    0.45
    امہ
    0.43
     مقاله
    0.43
    ERAL
    0.42
     مصرى
    0.42
     드라마
    0.42
     พร้อม
    0.42
     trafi
    0.42
     فلسط
    0.41
    Activations Density 0.004%

    No Known Activations