© 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. 22-GEMMASCOPE-RES-131K
    7. 26424
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

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

    The neuron strongly activates on standalone numeric tokens (e.g. “82”), i.e. it detects numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.62
     Италијани
    -1.13
     bicicleta
    -1.08
     blusa
    -1.05
     responde
    -1.04
    לה
    -1.03
    ContentAlignment
    -1.03
     ricas
    -1.02
     tatuaje
    -1.01
     compacto
    -1.01
    POSITIVE LOGITS
    尔的
    1.10
     crescita
    1.09
    abetes
    1.07
     vorne
    1.05
    なども
    1.03
    engarkan
    1.03
     fenô
    1.02
    一つの
    1.02
    ligne
    1.00
    形成了
    0.99
    Activations Density 0.000%

    No Known Activations