© 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. 71132
    Prev
    Next
    INDEX
    Explanations

    LESSEN project work package leaders

    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
    م
    0.50
    ИК
    0.42
     FAM
    0.42
     의미
    0.41
    ふわ
    0.41
    रम
    0.41
    તન
    0.41
     футбо
    0.40
    뀌
    0.40
    甕
    0.39
    POSITIVE LOGITS
     রাস্তায়
    0.48
     Straßen
    0.46
     óptica
    0.46
     phố
    0.46
     AliExpress
    0.45
     rápido
    0.44
     küçük
    0.44
     gráficos
    0.44
     suscipit
    0.44
     após
    0.43
    Activations Density 0.004%

    No Known Activations