© 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. 84298
    Prev
    Next
    INDEX
    Explanations

    choice and comparison

    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
    다고
    0.40
     embody
    0.39
    或者
    0.39
    あるいは
    0.39
     ahí
    0.39
     rags
    0.38
     fenders
    0.38
    艾
    0.36
    A
    0.35
    もしくは
    0.34
    POSITIVE LOGITS
     enfermedades
    0.49
     penyakit
    0.46
     친구
    0.44
    ᐈ
    0.44
     doenças
    0.43
    詿
    0.42
     עם
    0.42
     กับ
    0.42
    तीन
    0.42
     डर
    0.41
    Activations Density 0.009%

    No Known Activations