© 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. 90380
    Prev
    Next
    INDEX
    Explanations

    code assignments

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

    The neuron fires on user-defined identifiers (variable or instance names) in code.

    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
     its
    -1.18
    both
    -1.17
     BOTH
    -1.09
    も良い
    -1.03
     svoju
    -1.01
     both
    -0.97
    nischer
    -0.97
    疏
    -0.96
     Both
    -0.96
    さない
    -0.94
    POSITIVE LOGITS
     =
    3.27
     $=$
    2.16
    =
    1.81
     $=
    1.70
     $=\
    1.57
    }}=
    1.55
     =\
    1.55
    ＝
    1.47
    }=\
    1.45
     = 
    1.40
    Activations Density 0.015%

    No Known Activations