© 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. 40-GEMMASCOPE-2-RES-262K
    7. 29590
    Prev
    Next
    INDEX
    Explanations

    objects from

    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_40_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
    żyć
    0.41
     ใ
    0.37
     Bouch
    0.36
    osław
    0.35
     Perkenalkan
    0.35
     ባህ
    0.35
    美人
    0.34
     Вайлд
    0.34
    刚
    0.34
     kaha
    0.34
    POSITIVE LOGITS
     objects
    1.17
    objects
    1.16
    Objects
    1.09
     Objects
    1.09
     objetos
    1.02
     объектов
    0.89
     objek
    0.89
     объекты
    0.83
     object
    0.82
     oggetti
    0.81
    Activations Density 0.001%

    No Known Activations