© 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. 8389
    Prev
    Next
    INDEX
    Explanations

    step-by-step thinking

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

    The neuron fires on words and phrases that denote cognitive activity or abstract thought—terms like think, idea, imagine, figure, means, and similar expressions of mental reflection.

    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
    RO
    1.26
    я
    1.24
    7
    1.17
    6
    1.13
    8
    1.11
     발생하는
    1.09
    5
    1.08
    9
    1.07
    సూరు
    1.06
    4
    1.06
    POSITIVE LOGITS
     conceptions
    1.27
    انيا
    1.17
    思路
    1.16
     множество
    1.16
    ólogo
    1.13
     philosoph
    1.10
    思维
    1.10
     conceive
    1.09
     devised
    1.08
    isations
    1.07
    Activations Density 2.828%

    No Known Activations