© 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-262K
    4. 18192
    Prev
    Next
    INDEX
    Explanations

    sum, total, chorus

    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
    Hall
    0.39
    צ
    0.37
    朐
    0.35
     bengal
    0.34
    HP
    0.33
     cdot
    0.33
    ไ
    0.33
    ซ
    0.33
     klas
    0.33
     alot
    0.33
    POSITIVE LOGITS
     same
    0.75
    same
    0.71
     misma
    0.65
     அதே
    0.64
     stessi
    0.64
     dezelfde
    0.63
    ibid
    0.63
    同样的
    0.62
    同じ
    0.62
     aynı
    0.61
    Activations Density 0.276%

    No Known Activations