© 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. 39910
    Prev
    Next
    INDEX
    Explanations

    multilingual content or diverse concepts

    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
    ף
    0.49
    сии
    0.43
    ERY
    0.41
    ATT
    0.40
    :
    0.39
    स्ती
    0.38
    raises
    0.38
    tea
    0.38
    ги
    0.38
    сия
    0.38
    POSITIVE LOGITS
     जिनमें
    0.46
     معك
    0.45
     transcend
    0.43
     其他
    0.43
     ഇപ്പോള്‍
    0.43
    🥲
    0.42
    openweathermap
    0.41
     overcome
    0.41
     இப்போது
    0.41
     gemeinsame
    0.41
    Activations Density 0.005%

    No Known Activations