© 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. 12097
    Prev
    Next
    INDEX
    Explanations

    special characters, punctuation, or multi-language words

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

    The neuron responds to unusual or low‐frequency words—i.e. rare tokens that stand out in the text.

    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
    стей
    0.87
    TreeNavigator
    0.86
     convencional
    0.80
    ]'
    0.80
    Tp
    0.79
    ]')
    0.78
    словия
    0.77
     примене
    0.77
    ن
    0.74
     lashes
    0.73
    POSITIVE LOGITS
    騏
    0.82
    絆
    0.82
    ৮
    0.80
     Saves
    0.77
     এদিকে
    0.75
     équip
    0.74
     queste
    0.73
     Được
    0.73
     pant
    0.70
     هذه
    0.70
    Activations Density 0.000%

    No Known Activations