© 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. 116851
    Prev
    Next
    INDEX
    Explanations

    numbers and general terms

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

    The neuron is selectively activating on capitalized words used as list or title items (e.g. the checklist entries “Controls,” “Instruments,” “Gas,” “Attitude,” “Run-Up,” or the exclamatory phrase “Jolly Good Show!”).

    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
    代目
    -0.89
    =[]
    -0.81
     imo
    -0.76
    DOCTYPE
    -0.74
     ujednoznacz
    -0.74
    =[];
    -0.72
     nghệ
    -0.71
     IMO
    -0.70
     Studies
    -0.69
    cluster
    -0.69
    POSITIVE LOGITS
     PPR
    1.09
     chaps
    0.87
    攤
    0.86
    irmanship
    0.82
     silnik
    0.80
    melding
    0.77
    ämp
    0.77
     Exec
    0.77
    freq
    0.77
     utilizz
    0.75
    Activations Density 0.005%

    No Known Activations