© 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. 127919
    Prev
    Next
    INDEX
    Explanations

    code identifiers after

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

    The neuron fires on tokens naming Apache Mesos ecosystem components or related code identifiers (e.g. “mesos,” “mesosphere,” “marathon,” “task,” “offer,” “agent”).

    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
    secutions
    -1.77
     omdat
    -1.62
     république
    -1.55
    
    -1.51
    AHUL
    -1.47
    密的
    -1.47
     zů
    -1.45
    臯
    -1.44
    atoga
    -1.43
    Precalculus
    -1.41
    POSITIVE LOGITS
    ↵↵
    1.49
     currently
    1.43
     Unfortunately
    1.38
     Not
    1.38
     Especially
    1.35
     Currently
    1.34
    Причины
    1.33
     эффективности
    1.31
     Really
    1.30
    所说的
    1.30
    Activations Density 0.009%

    No Known Activations