© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108082
    Prev
    Next
    INDEX
    Explanations

    jetbrains ide components

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

    The neuron activates on programming‐language source‐file prologues and boilerplate (license/copyright headers, “package” and “import” declarations, etc.).

    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
     pola
    -0.82
     Оте
    -0.81
    сько
    -0.77
    National
    -0.76
    Blockly
    -0.75
    czak
    -0.75
     desayuno
    -0.74
    хла
    -0.73
    ську
    -0.73
    ListTile
    -0.73
    POSITIVE LOGITS
     IDEA
    1.27
    jetbrains
    1.16
     Idea
    1.05
    noinspection
    1.05
    intellij
    1.00
    psi
    0.99
     idea
    0.98
    idea
    0.94
    єр
    0.90
     Psi
    0.89
    Activations Density 0.082%

    No Known Activations