© 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. 10-GEMMASCOPE-RES-131K
    7. 59592
    Prev
    Next
    INDEX
    Explanations

    chromatin structure and modification

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

    terms related to chromatin, histone, and transcription factors in scientific literature.

    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
     Dinas
    -1.61
    probably
    -1.36
    🦣
    -1.35
    鼍
    -1.34
     aksesuar
    -1.34
     pleaſure
    -1.33
    (),
    -1.33
     spesifik
    -1.32
    푏
    -1.31
    mators
    -1.30
    POSITIVE LOGITS
    第六
    1.34
    īg
    1.31
     at
    1.31
    <i>
    1.27
    第八
    1.18
    ไม่
    1.16
     only
    1.14
     turning
    1.14
    第七
    1.12
     not
    1.10
    Activations Density 0.240%

    No Known Activations