© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7668
    Prev
    Next
    INDEX
    Explanations

    the living

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

    This neuron detects isolated single-letter initials followed by a period (as used in personal names).

    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_31_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
     सिर्फ
    0.64
     прият
    0.63
     구현
    0.60
     થઈ
    0.59
     gegründet
    0.57
    
    0.57
     تريد
    0.57
     முதுகு
    0.56
     ទ
    0.56
     အ
    0.56
    POSITIVE LOGITS
     logiciel
    0.90
     lockdowns
    0.89
     läk
    0.89
     Luftwaffe
    0.88
     logiciels
    0.86
     longing
    0.85
     Leistungen
    0.84
     laranja
    0.83
     ļ
    0.82
     logros
    0.82
    Activations Density 2.060%

    No Known Activations