© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2666
    Prev
    Next
    INDEX
    Explanations

    touring bicycles and cyclists

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

    The neuron selectively activates on numeric tokens or digits (i.e. any token containing a number).

    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
    冼
    -0.79
    ɵɵelement
    -0.73
    рка
    -0.71
     Contemporary
    -0.71
    :**
    -0.71
    比較的
    -0.69
    خوری
    -0.69
     зона
    -0.69
    ディース
    -0.68
     Skrill
    -0.68
    POSITIVE LOGITS
     touring
    1.19
    Cycles
    1.08
     cyclists
    1.06
     Cycles
    1.03
     Touring
    1.00
     bicy
    0.98
    fiets
    0.96
     bicycle
    0.94
     cyc
    0.91
     Bicycle
    0.91
    Activations Density 0.017%

    No Known Activations