© 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. 66576
    Prev
    Next
    INDEX
    Explanations

    import/include statements

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

    The neuron is looking for numeric tokens (i.e. sequences of digits) 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
     ateliers
    -0.93
     Nabi
    -0.85
     Andante
    -0.82
     består
    -0.79
     atelier
    -0.79
     川
    -0.79
     男女
    -0.78
    нгредіє
    -0.77
    衽
    -0.76
    CONCLUS
    -0.76
    POSITIVE LOGITS
    orthand
    0.87
    時
    0.86
     сор
    0.80
    时
    0.80
    ごちそうさまでした
    0.79
    dotenv
    0.75
     pellets
    0.75
     Ereign
    0.74
    UGS
    0.74
    riteria
    0.74
    Activations Density 0.015%

    No Known Activations