© 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. 78652
    Prev
    Next
    INDEX
    Explanations

    css imports

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

    This neuron activates on standalone numeric tokens (i.e. 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
     Tampoco
    -0.85
     Incluso
    -0.82
     Algunas
    -0.81
    ereka
    -0.81
     Utilizamos
    -0.81
    gehend
    -0.78
    痾
    -0.78
     Prenez
    -0.78
     Lleva
    -0.78
     récord
    -0.78
    POSITIVE LOGITS
    App
    1.31
     App
    0.97
    normalize
    0.93
    global
    0.85
    index
    0.83
    reset
    0.83
     pérd
    0.79
    🏑
    0.77
     normalize
    0.77
    Reset
    0.77
    Activations Density 0.002%

    No Known Activations