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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 5382
    Prev
    Next
    INDEX
    Explanations

    people searching for content

    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_40_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
     dbcontext
    0.41
     isEqual
    0.39
    ⴰ
    0.38
     quadrilateral
    0.38
     sigmoid
    0.36
    ссмо
    0.35
     hexadecimal
    0.35
     одном
    0.34
     각각
    0.33
    🙍
    0.33
    POSITIVE LOGITS
     people
    2.11
    人们
    1.99
     사람들이
    1.98
    people
    1.90
     людям
    1.85
    人們
    1.84
     लोगों
    1.83
     люди
    1.82
     الناس
    1.73
     ljudi
    1.73
    Activations Density 0.033%

    No Known Activations