© 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. 22295
    Prev
    Next
    INDEX
    Explanations

    public methods and properties

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

    The neuron is detecting numeric literal tokens (e.g. integers and floats) in code.

    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
     навіть
    -1.73
     even
    -1.70
    仨
    -1.67
     vacunas
    -1.63
     після
    -1.60
     promete
    -1.60
     даже
    -1.58
    Öl
    -1.55
     résistant
    -1.55
     BoxFit
    -1.52
    POSITIVE LOGITS
     of
    2.61
    =?,
    1.55
     perche
    1.34
    lerin
    1.33
     ons
    1.33
     her
    1.32
     varie
    1.30
     ſou
    1.29
    🥷
    1.28
    возмо
    1.26
    Activations Density 0.241%

    No Known Activations