© 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. 7107
    Prev
    Next
    INDEX
    Explanations

    Roman shift previous search

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

    The neuron intensely activates on tokens that represent whole words (i.e. complete standalone WordPiece tokens) rather than on subword fragments.

    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
    ए
    0.98
    лната
    0.92
     връ
    0.87
    И
    0.85
    lanelet
    0.84
    на
    0.82
    même
    0.82
    exemple
    0.81
    вър
    0.80
    applicable
    0.80
    POSITIVE LOGITS
     velocities
    0.89
     Enzymes
    0.81
     portability
    0.73
     movements
    0.73
     shades
    0.73
    :
    0.72
    estone
    0.71
     Solubility
    0.71
    ainty
    0.70
    ushes
    0.70
    Activations Density 0.000%

    No Known Activations