© 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. 22-GEMMASCOPE-RES-131K
    7. 39235
    Prev
    Next
    INDEX
    Explanations

    code syntax and specific phrases

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

    The neuron primarily activates on numeric tokens (digits and number-like strings) wherever they appear.

    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
     Terbaru
    -1.30
     Tempat
    -1.23
     Censo
    -1.21
    seperti
    -1.20
     Entdecken
    -1.20
    thenburg
    -1.20
     Lös
    -1.19
     länder
    -1.18
    mereka
    -1.16
    ﻷ
    -1.16
    POSITIVE LOGITS
     you
    1.32
     to
    1.30
     first
    1.26
     command
    1.19
     though
    1.13
     häufiger
    1.09
    ʖ
    1.08
    鹉
    1.01
    起動
    0.99
     night
    0.99
    Activations Density 0.001%

    No Known Activations