© 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. 84544
    Prev
    Next
    INDEX
    Explanations

    COD and TB abbreviations

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

    abbreviations in scientific and medical texts, particularly chemical and medical acronyms.

    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
    </h3>
    -3.66
    <em>
    -3.03
    廡
    -2.75
     −
    -2.72
    ,”
    -2.67
    拶
    -2.67
    It
    -2.63
    </em>
    -2.58
    नलोड
    -2.44
    </h6>
    -2.42
    POSITIVE LOGITS
    และ
    2.56
    鶿
    2.34
    เพราะ
    2.31
     使っ
    2.23
    ﻞ
    2.11
    孖
    2.06
    孓
    2.06
    謌
    2.06
    目的是
    2.03
    錨
    2.00
    Activations Density 0.017%

    No Known Activations