© 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. 22-GEMMASCOPE-RES-131K
    7. 9544
    Prev
    Next
    INDEX
    Explanations

    single or one

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

    This neuron fires on programming‐related tokens—especially keywords and common method or type names (e.g. else, replace, Symbol).

    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
     and
    -1.05
    VarChar
    -0.92
     consortium
    -0.84
    MetaType
    -0.83
     remote
    -0.82
    傷害
    -0.81
     Institute
    -0.80
    ние
    -0.78
     bezüglich
    -0.77
     trzec
    -0.77
    POSITIVE LOGITS
     single
    1.82
    单个
    1.54
    Single
    1.49
    single
    1.46
     singular
    1.41
    SINGLE
    1.41
     pojed
    1.36
    unica
    1.30
    只有一个
    1.24
    单
    1.24
    Activations Density 0.020%

    No Known Activations