© 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. 22-GEMMASCOPE-RES-131K
    7. 72035
    Prev
    Next
    INDEX
    Explanations

    code block comparisons

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

    The neuron strongly activates on programming‐related tokens—keywords, operators, punctuation, and other code syntax elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    いただけます
    -1.02
    complished
    -1.01
     who
    -1.01
    剧照
    -1.00
     bisous
    -0.99
    pergillus
    -0.96
     ""));
    -0.95
    complish
    -0.93
    setHorizontal
    -0.90
    after
    -0.89
    POSITIVE LOGITS
    قامة
    1.05
    9
    1.03
     protocols
    1.01
     abnormally
    0.98
    8
    0.93
    0
    0.92
     enfer
    0.91
     peor
    0.90
     variations
    0.90
    AndWait
    0.89
    Activations Density 0.001%

    No Known Activations