© 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. 67843
    Prev
    Next
    INDEX
    Explanations

    intercepting or intervening

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

    The main thing this neuron does is find occurrences of the root “intercept” (in any form or tense).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    她
    -2.70
    an
    -2.50
    </i>
    -2.45
    THE
    -2.33
    en
    -2.30
    時に
    -2.28
    他们
    -2.25
    </h1>
    -2.23
    你
    -2.17
    ため
    -2.11
    POSITIVE LOGITS
    檍
    3.31
    潆
    2.92
    ).
    2.77
    驀
    2.67
    кзак
    2.61
    ︲
    2.59
    莜
    2.58
    ꔛ
    2.58
    偁
    2.53
    鹟
    2.52
    Activations Density 0.002%

    No Known Activations