© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11479
    Prev
    Next
    INDEX
    Explanations

    less than eight years

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

    The neuron strongly activates on numeric tokens representing floating‐point or precise quantitative values (e.g. “1452.3611,” “1000 Mg,” “1426.938”), i.e. detailed numeric figures.

    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
    ﻤ
    0.91
     Harus
    0.87
    uristic
    0.85
    ure
    0.81
    প্রিল
    0.81
    ﺮ
    0.80
    alamat
    0.79
    اب
    0.79
    াহ
    0.79
    ৪০
    0.79
    POSITIVE LOGITS
     है
    0.78
    Opts
    0.69
     års
    0.68
     형태로
    0.66
     particulières
    0.66
    ઁ
    0.66
     différentes
    0.66
     있다
    0.65
     તેની
    0.63
     ưu
    0.63
    Activations Density 0.000%

    No Known Activations