© 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. 7624
    Prev
    Next
    INDEX
    Explanations

    game logic

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

    The neuron strongly activates on low‐frequency or otherwise unusual tokens (i.e. rare words).

    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
     ನಾಲ್
    0.76
     FAV
    0.75
     factorization
    0.75
     カル
    0.74
     CrossFit
    0.73
    ড
    0.73
     ಎರಡು
    0.72
    썬
    0.72
     Natasha
    0.71
    丕
    0.70
    POSITIVE LOGITS
     saka
    0.82
     keperluan
    0.79
     deverá
    0.78
    tolyl
    0.73
    teile
    0.73
     Halb
    0.73
    その他の
    0.72
     klub
    0.72
    機械
    0.72
    shu
    0.70
    Activations Density 0.000%

    No Known Activations