© 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. 14185
    Prev
    Next
    INDEX
    Explanations

    code elements

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

    The main thing this neuron does is detect numeric literal tokens (numbers) in the 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
     új
    -1.30
    があり
    -1.24
     when
    -1.23
    𓐍
    -1.20
    はとても
    -1.17
     évêque
    -1.16
    vosť
    -1.16
    avits
    -1.15
    もしか
    -1.14
    rdı
    -1.14
    POSITIVE LOGITS
     them
    1.25
    様な
    1.18
     erfolgre
    1.18
     it
    1.17
    ものが
    1.17
    ときの
    1.16
    是怎么回事
    1.16
    ところに
    1.10
    黑的
    1.10
    已經
    1.09
    Activations Density 0.005%

    No Known Activations