© 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-65K
    7. 7172
    Prev
    Next
    INDEX
    Explanations

    foreign language datasets

    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_65k_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
    ing
    0.45
    .
    0.43
    ↵↵
    0.43
    rab
    0.41
    y
    0.40
    ઈ
    0.39
    <h2>
    0.38
     proceed
    0.38
     $
    0.38
    lear
    0.37
    POSITIVE LOGITS
    崞
    0.43
     வள்ளி
    0.41
    轻轻
    0.41
     এলি
    0.40
    rightsquigarrow
    0.40
    čnih
    0.39
     জ্ঞানের
    0.39
    揆
    0.39
    ្នាក់
    0.39
     ഒന്ന്
    0.39
    Activations Density 0.002%

    No Known Activations