© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37812
    Prev
    Next
    INDEX
    Explanations

    initials followed by name or medical condition

    np_acts-logits-general · gemini-2.5-flash-lite

    names of people, particularly Nordic or Scandinavian names starting with letters like Bj, Sj, or TJ.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "%(
    -0.82
     practitioner
    -0.74
    ATHAN
    -0.73
    Compact
    -0.72
     sarees
    -0.71
    Erm
    -0.71
    abr
    -0.71
    мето
    -0.71
     subsequently
    -0.69
    اقت
    -0.69
    POSITIVE LOGITS
    DJ
    0.99
     SJ
    0.94
     MJ
    0.94
     HJ
    0.93
     DJ
    0.87
    PJ
    0.82
     RJ
    0.79
     PJ
    0.79
    MJ
    0.77
    gj
    0.77
    Activations Density 0.018%

    No Known Activations