© 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. 2889
    Prev
    Next
    INDEX
    Explanations

    Court of Appeals

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

    This neuron specializes in spotting programming‐language identifiers and keywords (e.g. import, Test, Assert, argv) in code snippets.

    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
    rrrrrrrr
    -0.84
     snabb
    -0.82
    compatibility
    -0.81
    īgas
    -0.78
     enligt
    -0.75
     flanking
    -0.75
     pajak
    -0.74
     vissza
    -0.73
    parente
    -0.73
    *'
    -0.73
    POSITIVE LOGITS
     виправивши
    0.83
     rather
    0.82
    Amar
    0.82
     begins
    0.76
    OrDefault
    0.75
    생
    0.75
    initComponents
    0.75
    IEC
    0.73
    submenu
    0.71
    급
    0.71
    Activations Density 0.001%

    No Known Activations