© 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. 70144
    Prev
    Next
    INDEX
    Explanations

    label definition file

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

    The neuron overwhelmingly lights up on occurrences of “label” or “labels” (e.g. as keys or identifiers in code/config).

    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
     Rector
    -0.81
     gouver
    -0.79
    mited
    -0.79
    bish
    -0.76
     ال
    -0.75
    갚
    -0.75
     Highest
    -0.73
     augus
    -0.71
    Higher
    -0.71
     juez
    -0.71
    POSITIVE LOGITS
    Lbl
    0.93
    label
    0.92
    setLabel
    0.90
     labeling
    0.86
    itäts
    0.85
    ocused
    0.85
     label
    0.82
    Label
    0.81
     Label
    0.80
     LAB
    0.79
    Activations Density 0.026%

    No Known Activations