© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2599
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by periods

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

    This neuron detects single uppercase letters followed by a period (initials or acronyms).

    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
    u
    0.82
    et
    0.70
    ان
    0.66
    uws
    0.66
    uus
    0.64
    jogo
    0.63
    en
    0.60
    m
    0.60
    atasi
    0.59
    on
    0.58
    POSITIVE LOGITS
     Messrs
    0.59
     Ведь
    0.52
     Cumber
    0.52
    상의
    0.52
     Councils
    0.51
     Sufficient
    0.50
    Ｉ
    0.50
    ૭
    0.50
     Yatha
    0.50
     diminish
    0.49
    Activations Density 0.011%

    No Known Activations