© 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. 11759
    Prev
    Next
    INDEX
    Explanations

    according to sources

    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
     vaše
    0.52
    Ა
    0.50
     voglio
    0.45
     ඔබේ
    0.45
    あなたの
    0.45
     gerar
    0.45
     ਤੁਹਾ
    0.44
     guérir
    0.44
     نبدا
    0.44
    Ე
    0.44
    POSITIVE LOGITS
     according
    1.18
     According
    1.05
    According
    1.02
     menurut
    1.01
    据
    0.98
     según
    0.95
     volgens
    0.95
    according
    0.92
     reportedly
    0.90
     według
    0.89
    Activations Density 0.048%

    No Known Activations