© 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. 103752
    Prev
    Next
    INDEX
    Explanations

    public with final or qc

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

    This neuron detects Java source‐code declarations and import/package statements (i.e. code structural tokens like “package,” “import,” dots, semicolons, and class/function names).

    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
     логоти
    -0.89
     ചെയ
    -0.86
    Furthermore
    -0.82
    espero
    -0.82
    EVEN
    -0.78
    idians
    -0.77
    ߎ
    -0.77
     bewilder
    -0.77
    TRON
    -0.76
    Espagne
    -0.75
    POSITIVE LOGITS
    อด
    0.91
     rgb
    0.80
     hear
    0.75
    сив
    0.75
    チョコ
    0.74
    atus
    0.73
    crt
    0.73
    雪花
    0.73
     infar
    0.73
    пис
    0.72
    Activations Density 0.006%

    No Known Activations