© 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. 31-GEMMASCOPE-2-RES-262K
    7. 200532
    Prev
    Next
    INDEX
    Explanations

    target audience

    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
     production
    0.48
    ر
    0.45
    म
    0.44
    azität
    0.44
    م
    0.43
    ﺮ
    0.43
    č
    0.43
    verture
    0.42
     secretly
    0.42
     función
    0.42
    POSITIVE LOGITS
    အနေ
    0.56
    ifika
    0.46
     黑
    0.46
     Agricultura
    0.46
     Agro
    0.45
     Eminent
    0.45
    连忙
    0.44
     spacers
    0.44
     Element
    0.44
     Etienne
    0.44
    Activations Density 0.000%

    No Known Activations