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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92742
    Prev
    Next
    INDEX
    Explanations

    Regal RA, Trace elements

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

    technical content in programming and blockchain contexts.

    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
     because
    -0.85
     thinks
    -0.83
     while
    -0.77
     keju
    -0.76
     after
    -0.73
     owners
    -0.72
     usually
    -0.71
     people
    -0.71
     only
    -0.71
     one
    -0.71
    POSITIVE LOGITS
     Binance
    1.21
     BNB
    1.09
    Binance
    0.88
     AEW
    0.85
    DWORD
    0.84
     Pensacola
    0.83
    LÄ
    0.82
    踹
    0.82
    FlatList
    0.81
     鸡
    0.81
    Activations Density 0.001%

    No Known Activations