© 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. 50707
    Prev
    Next
    INDEX
    Explanations

    Tom Robinson, wagging, GPUs for, jokes

    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
    Ка
    0.50
    บ
    0.49
    Atual
    0.47
    Как
    0.46
    カ
    0.46
    Τα
    0.45
     статьи
    0.45
    贰
    0.45
     গভর্ন
    0.45
    Мо
    0.45
    POSITIVE LOGITS
     pentru
    0.44
     fpr
    0.43
    សម្រាប់ការ
    0.42
     SPSS
    0.42
     dla
    0.42
     SPT
    0.41
     voor
    0.40
     neuropath
    0.39
     Table
    0.38
     phil
    0.38
    Activations Density 0.010%

    No Known Activations