© 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. 31752
    Prev
    Next
    INDEX
    Explanations

    def down

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

    The neuron fires on programming‐language structural keywords and block delimiters (e.g. def/end in Ruby, import/export in JS/TS, public/async in TS/C#, 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
    amientos
    -0.94
     capteur
    -0.86
    arschu
    -0.85
    зопас
    -0.82
     mended
    -0.79
    indung
    -0.78
    offsetWidth
    -0.78
    Ỏ
    -0.77
    ANDUM
    -0.77
    از
    -0.75
    POSITIVE LOGITS
     down
    1.47
    down
    1.20
     DOWN
    1.12
    Down
    1.11
     tearDown
    1.01
     Down
    0.98
     downward
    0.89
     downside
    0.88
    DOWN
    0.88
     inversely
    0.85
    Activations Density 0.002%

    No Known Activations