© 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. 30174
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
     parody
    0.50
     sleep
    0.45
    Sleep
    0.44
    睡眠
    0.44
     leaking
    0.42
     peek
    0.41
     consp
    0.40
    인
    0.40
    ють
    0.40
     mathvariant
    0.40
    POSITIVE LOGITS
     حروف
    0.49
     రోజుల
    0.49
     ግራም
    0.48
     Eine
    0.47
     ቀን
    0.47
     进行
    0.47
    籵
    0.46
    itre
    0.46
    avkhat
    0.45
     باي
    0.44
    Activations Density 0.001%

    No Known Activations