© 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. 69837
    Prev
    Next
    INDEX
    Explanations

    Big Ben, Liviu, cost effectiveness

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

    The neuron fires strongly on numeric tokens and measurements (i.e. sequences of digits or numbers).

    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
    coral
    -0.77
    bauten
    -0.69
     bouwen
    -0.69
    ディダス
    -0.69
    canny
    -0.68
     mailbox
    -0.68
    嚏
    -0.66
     dood
    -0.66
     corral
    -0.66
     coral
    -0.66
    POSITIVE LOGITS
     belf
    1.15
     clavier
    1.13
     зво
    1.01
     inscriptions
    0.94
    EMY
    0.92
    rope
    0.88
     حم
    0.87
     ropes
    0.86
     malha
    0.86
     Patt
    0.85
    Activations Density 0.009%

    No Known Activations