© 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. 91677
    Prev
    Next
    INDEX
    Explanations

    java import statements

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

    The neuron consistently lights up on “import” statements (particularly Java imports) in source‐code files.

    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
    textra
    -0.91
    不起
    -0.88
    穿搭
    -0.82
                           
    -0.82
    kozá
    -0.81
    edakan
    -0.78
    auces
    -0.77
    一百
    -0.76
     jelen
    -0.76
    年後
    -0.75
    POSITIVE LOGITS
     java
    1.73
    import
    1.34
    java
    0.98
    Importante
    0.88
     including
    0.84
    Ljava
    0.82
    ⁇
    0.82
     vergangenen
    0.81
    illigen
    0.81
     berpikir
    0.81
    Activations Density 0.097%

    No Known Activations