© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128920
    Prev
    Next
    INDEX
    Explanations

    breakpoint or breakpoints

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

    references to "breakpoint" or "break point" in programming and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is tuned to detect the term “breakpoint.”

    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
     There
    -2.56
    та
    -2.55
    .,
    -2.48
     When
    -2.30
    }
    -2.20
    )
    -2.19
    лением
    -2.17
    ну
    -2.17
    </i>
    -2.14
     faked
    -2.13
    POSITIVE LOGITS
    ではまた
    2.56
    鈊
    2.53
    趼
    2.48
    盉
    2.36
    ѣмъ
    2.36
    汭
    2.30
    珰
    2.28
    淠
    2.25
    砗
    2.23
    臜
    2.23
    Activations Density 0.007%

    No Known Activations