© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9291
    Prev
    Next
    INDEX
    Explanations

    classic, future, potential

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

    The neuron fires strongly on long, content-heavy or less common “information-rich” words (i.e. unusually long or rare vocabulary tokens).

    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_31_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
    щиков
    0.64
    0.62
     Kessler
    0.62
    、
    0.62
     Rc
    0.61
    み
    0.61
     RN
    0.60
     Todo
    0.59
     والوں
    0.59
    ProjectReference
    0.59
    POSITIVE LOGITS
     rendement
    0.71
    <unused2148>
    0.71
     düzenlenen
    0.70
     wannan
    0.69
     changement
    0.68
     outpouring
    0.68
     konuda
    0.68
     cairan
    0.67
     danske
    0.67
     gelişmeler
    0.67
    Activations Density 0.874%

    No Known Activations