© 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. 34-GEMMASCOPE-RES-131K
    7. 117668
    Prev
    Next
    INDEX
    Explanations

    start of phrases

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

    The neuron is strongly activated by C/C++ header‐file include directives (i.e. “#include …” lines).

    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
    tide
    -0.82
     Expenditure
    -0.80
     Perception
    -0.79
     возрасте
    -0.76
    stacked
    -0.75
     drunken
    -0.73
    tése
    -0.71
    ਤੀ
    -0.71
     الرسمي
    -0.71
     подрост
    -0.70
    POSITIVE LOGITS
     Adirond
    0.99
    新潟
    0.96
     concurs
    0.88
     überall
    0.82
    ódz
    0.82
     dunque
    0.77
    These
    0.76
     نباش
    0.76
     adage
    0.75
    бом
    0.75
    Activations Density 0.000%

    No Known Activations