© 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. 32021
    Prev
    Next
    INDEX
    Explanations

    code elements

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

    The neuron fires on programming identifiers—e.g. variable names, function or class names, and other code symbols.

    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
     korrekt
    -1.05
    celtic
    -0.93
     retten
    -0.93
     dáms
    -0.90
    шед
    -0.89
    joel
    -0.89
    🩳
    -0.89
    gabriel
    -0.88
    detek
    -0.88
    stephen
    -0.86
    POSITIVE LOGITS
    not
    1.06
     WALTZ
    1.05
    了一個
    1.02
    环节
    1.00
    出來的
    1.00
    although
    1.00
    ets
    1.00
     altra
    0.98
    isGrid
    0.98
    ve
    0.97
    Activations Density 0.063%

    No Known Activations