© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5282
    Prev
    Next
    INDEX
    Explanations

    words starting with li

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

    The neuron highly activates on capitalized name‐like or place‐like tokens—i.e. proper nouns or named entities.

    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
     Journals
    0.64
     impressively
    0.59
     Neat
    0.58
     obliquely
    0.57
    ગાહી
    0.57
     организации
    0.56
    딴
    0.55
     कथन
    0.55
     imaginary
    0.54
     Practices
    0.54
    POSITIVE LOGITS
    apunov
    0.80
    chtenstein
    0.69
    utenant
    0.68
    ফলে
    0.65
    ocaine
    0.62
    蜴
    0.61
    abilities
    0.59
    utenants
    0.58
    اقة
    0.57
     নিকটে
    0.57
    Activations Density 0.470%

    No Known Activations