© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59037
    Prev
    Next
    INDEX
    Explanations

    code structure and keywords

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

    The neuron fires strongly on numeric literals (and related punctuation) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    𝟒
    -1.04
    ଵ
    -1.03
     (
    -1.02
    mappedBy
    -1.02
     kertoo
    -1.01
    providedIn
    -1.00
    </tfoot>
    -0.96
     définiti
    -0.95
     tuot
    -0.94
     "
    -0.94
    POSITIVE LOGITS
    )
    1.83
     **
    1.42
     )
    1.41
     ).
    1.38
    )#
    1.35
    **
    1.34
    .)
    1.30
    ).
    1.29
    ）
    1.27
    ↵
    1.16
    Activations Density 0.009%

    No Known Activations