© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84103
    Prev
    Next
    INDEX
    Explanations

    children and family relationships

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

    This neuron tracks how many times each token has already appeared in the document, i.e. it activates in proportion to the token’s prior occurrence count.

    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
    Ольга
    -0.84
    Dr
    -0.80
     strick
    -0.79
    Ƹ
    -0.78
     horiz
    -0.76
     audiobook
    -0.75
     Widow
    -0.75
     drab
    -0.74
     +.
    -0.74
     unsound
    -0.73
    POSITIVE LOGITS
     Joshua
    1.29
     Ethan
    1.19
     Dylan
    1.09
     Brandon
    0.98
     Matthew
    0.98
     Medien
    0.96
     Kevin
    0.95
     Sha
    0.94
     Daniel
    0.91
     twins
    0.90
    Activations Density 0.026%

    No Known Activations