© 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. 45177
    Prev
    Next
    INDEX
    Explanations

    relationship between

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

    The neuron activates on numeric tokens (quantities, measurements, and other 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_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
    irée
    -1.34
    yoruz
    -1.34
     их
    -1.32
     espagne
    -1.25
     résister
    -1.23
     ziem
    -1.21
     themſelves
    -1.21
    isissez
    -1.21
    ił
    -1.20
    ⤻
    -1.20
    POSITIVE LOGITS
     jednom
    1.36
     That
    1.23
     which
    1.21
    mieszkanie
    1.21
     with
    1.18
     new
    1.14
    Ḳ
    1.13
     nowych
    1.10
    をしていた
    1.09
    一時
    1.09
    Activations Density 0.222%

    No Known Activations