© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 20737
    Prev
    Next
    INDEX
    Explanations

    generating code examples

    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
    中央
    0.40
    ская
    0.38
     শ্রবণ
    0.37
     Using
    0.37
     предвари
    0.37
     отобра
    0.36
    τερ
    0.35
    体
    0.34
    
    0.34
    ---
    0.34
    POSITIVE LOGITS
     heav
    0.45
     hoax
    0.45
    หลากหลาย
    0.45
     diverses
    0.45
     intimidation
    0.44
     nob
    0.44
     తాజాగా
    0.43
     diversos
    0.43
     Goodreads
    0.43
     নিয়েছে
    0.43
    Activations Density 0.413%

    No Known Activations