© 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. 47990
    Prev
    Next
    INDEX
    Explanations

    Neurokinin

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

    programming and technical documentation, particularly method calls and API references.

    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
    女兒
    -0.94
    给自己
    -0.87
     Marlins
    -0.82
    ってしまった
    -0.81
     imputation
    -0.79
    小伙伴
    -0.79
    を整
    -0.79
     Astros
    -0.78
    ようやく
    -0.77
    囂
    -0.77
    POSITIVE LOGITS
     Sk
    1.09
     SK
    1.01
     sk
    0.96
     Worcester
    0.93
     Massachusetts
    0.86
    籍
    0.86
    sk
    0.82
    쿼
    0.78
    windows
    0.78
    Massachusetts
    0.77
    Activations Density 0.006%

    No Known Activations