© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10184
    Prev
    Next
    INDEX
    Explanations

    HDAC inhibitors

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

    scientific and technical terminology, particularly biochemical terms and abbreviations.

    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_10/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
    >
    -1.92
    advantages
    -1.54
    弹窗
    -1.53
    「
    -1.52
     précie
    -1.52
    :"
    -1.52
    Most
    -1.50
    These
    -1.50
     coroa
    -1.49
    Also
    -1.47
    POSITIVE LOGITS
     you
    1.58
    </h1>
    1.53
     is
    1.45
    ίες
    1.40
     The
    1.34
    ?”
    1.34
    เขา
    1.32
    </b>
    1.30
     zweiter
    1.29
    );
    
    1.27
    Activations Density 0.026%

    No Known Activations