© 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. 25281
    Prev
    Next
    INDEX
    Explanations

    values independence

    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
    ση
    0.41
     ошибки
    0.40
    蜡
    0.40
    児
    0.38
     hígado
    0.38
    エラー
    0.38
     ошибка
    0.38
    壮
    0.38
    长时间
    0.37
    错误
    0.37
    POSITIVE LOGITS
     mereka
    0.54
     kanilang
    0.54
     pragmatic
    0.52
     ihre
    0.50
     त्यांच्या
    0.50
     Their
    0.48
     commandments
    0.47
     paradigma
    0.47
     their
    0.47
     principalmente
    0.47
    Activations Density 0.018%

    No Known Activations