© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 11918
    Prev
    Next
    INDEX
    Explanations

    United States, Group, subject, development

    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
     输出
    0.69
     Inbetriebnahme
    0.62
    唵
    0.61
    惊讶
    0.59
     Thermodynamic
    0.59
     మె
    0.57
    肿瘤
    0.57
     Hoàng
    0.57
     pulang
    0.56
    禳
    0.56
    POSITIVE LOGITS
    primarily
    0.76
    generally
    0.75
     may
    0.75
     generally
    0.71
     primarily
    0.70
    may
    0.69
     substantially
    0.68
    could
    0.67
    ]
    0.66
    we
    0.66
    Activations Density 0.034%

    No Known Activations