© 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. 10-GEMMASCOPE-RES-131K
    7. 99462
    Prev
    Next
    INDEX
    Explanations

    in

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

    The neuron is detecting floating‐point numeric tokens (numbers containing a decimal point, e.g. “114.5”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     riu
    -1.95
    神
    -1.77
    性价比
    -1.76
     lames
    -1.74
     wees
    -1.74
     baf
    -1.72
     porc
    -1.70
     mame
    -1.70
    ],
    -1.69
     maro
    -1.68
    POSITIVE LOGITS
     a
    2.11
    我真的
    1.86
    蕻
    1.84
     such
    1.83
     singularly
    1.82
    女友
    1.81
    珦
    1.77
     yüzde
    1.76
    koliv
    1.75
     cechy
    1.73
    Activations Density 0.018%

    No Known Activations