© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10894
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

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

    This neuron detects numeric tokens that include a decimal point (i.e. floating-point 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_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
    妧
    -2.09
    -
    -2.00
     några
    -1.81
    ,
    -1.69
     kazi
    -1.63
    {~
    -1.63
     ungefär
    -1.62
    蚰
    -1.61
    倹
    -1.59
    檍
    -1.59
    POSITIVE LOGITS
     is
    1.99
    ogados
    1.98
    緜
    1.95
    Skocz
    1.84
    ஂ
    1.84
    jetivo
    1.72
     the
    1.70
    豋
    1.70
     karena
    1.69
     With
    1.66
    Activations Density 0.022%

    No Known Activations