© 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. 73668
    Prev
    Next
    INDEX
    Explanations

    adipose tissue

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

    The neuron detects terms related to code libraries, frameworks, and programming interfaces, particularly in file imports and tech documentation.

    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
    0
    -2.97
    1
    -2.83
     {
    -2.81
    でも
    -2.58
    <i>
    -2.58
    the
    -2.39
    6
    -2.31
     avec
    -2.25
     The
    -2.22
     -
    -2.22
    POSITIVE LOGITS
     soo
    3.09
    僂
    2.75
    鲼
    2.56
    轳
    2.47
     contentious
    2.47
    嗱
    2.41
     Ihm
    2.39
    栳
    2.38
    ﮏ
    2.34
    妘
    2.33
    Activations Density 0.001%

    No Known Activations