© 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. 12676
    Prev
    Next
    INDEX
    Explanations

    travel arrangement

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

    The neuron primarily lights up on very common connective or “stop” words (e.g. so, to, be, is, that, etc.).

    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
     һ
    0.82
     верхней
    0.81
    ╭
    0.79
     первой
    0.79
     Մ
    0.78
     КС
    0.77
     корре
    0.77
     Кы
    0.77
     государственной
    0.77
     ҡ
    0.76
    POSITIVE LOGITS
     analogues
    0.82
    analog
    0.78
     analogue
    0.77
     machines
    0.76
     automobiles
    0.76
     électronique
    0.76
    ם
    0.75
    butt
    0.75
    os
    0.74
     consomm
    0.73
    Activations Density 0.001%

    No Known Activations