© 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. 34-GEMMASCOPE-RES-131K
    7. 81044
    Prev
    Next
    INDEX
    Explanations

    translated

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

    The neuron primarily detects numeric tokens (digits or numbers) in the text.

    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
    vri
    -0.94
     pesquis
    -0.92
    ִּ
    -0.92
     Napoleon
    -0.90
    "./
    -0.86
    话音
    -0.84
     fá
    -0.81
    ­
    -0.81
    бера
    -0.79
    esthes
    -0.79
    POSITIVE LOGITS
     translators
    0.96
     Translator
    0.94
     untranslated
    0.93
    Translated
    0.92
     Translated
    0.91
    ‌.
    0.90
    思わず
    0.89
    Translator
    0.88
    translated
    0.88
     translated
    0.85
    Activations Density 0.001%

    No Known Activations