© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40152
    Prev
    Next
    INDEX
    Explanations

    code imports and protocols

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

    The neuron strongly activates on numeric tokens (literal numbers) 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_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
     other
    -1.18
     another
    -1.16
    その他の
    -1.12
     each
    -1.06
     further
    -1.03
     Kooperation
    -1.02
     nachher
    -1.00
    全体の
    -1.00
     ordentlich
    -0.99
     additional
    -0.98
    POSITIVE LOGITS
    nós
    1.12
     synerg
    1.09
     transparentes
    1.06
    mazaki
    1.03
    rück
    1.03
    $<
    0.97
     génie
    0.96
    我们
    0.96
    štu
    0.96
    غال
    0.96
    Activations Density 0.045%

    No Known Activations