© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8867
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

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

    This neuron activates on tokens representing numeric values (especially decimals and other number strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lig
    0.82
    liği
    0.79
    rient
    0.72
     گ
    0.70
    と共に
    0.70
     Transcription
    0.70
     Тя
    0.69
     र
    0.68
     رشته
    0.67
     Продол
    0.67
    POSITIVE LOGITS
     nervioso
    0.96
     ciudadanos
    0.94
    occurrence
    0.88
    ar
    0.88
     utilisateurs
    0.85
     avaient
    0.84
     ocurrir
    0.83
     alarma
    0.82
     agir
    0.81
     dans
    0.80
    Activations Density 0.003%

    No Known Activations