© 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. 34-GEMMASCOPE-RES-131K
    7. 49584
    Prev
    Next
    INDEX
    Explanations

    this file

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

    The neuron is selectively activating on standalone numeric tokens (i.e. sequences of digits) in the document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Lü
    -0.93
     kutu
    -0.86
    Odpowiedz
    -0.85
    ラックス
    -0.84
     veli
    -0.82
    Lü
    -0.82
    vacation
    -0.81
    Referensi
    -0.81
    出来ました
    -0.81
     množ
    -0.79
    POSITIVE LOGITS
    さらに
    0.77
    提及
    0.75
    ル
    0.73
    und
    0.73
    DUR
    0.71
     می‌توان
    0.70
    Messaging
    0.69
    作業
    0.69
    her
    0.69
     palms
    0.69
    Activations Density 0.039%

    No Known Activations