© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14799
    Prev
    Next
    INDEX
    Explanations

    already, k, -

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

    The neuron strongly activates on capitalized tokens (i.e. words beginning with an uppercase letter).

    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
     Vereinig
    1.05
     localidades
    0.87
    쳤
    0.82
     भेजना
    0.80
    Objs
    0.79
    ﺀ
    0.77
    Mailer
    0.75
    ﺭ
    0.75
    心配
    0.75
     Egipto
    0.75
    POSITIVE LOGITS
     thermostat
    0.87
     oscilloscope
    0.81
     quitter
    0.78
     fluctuation
    0.76
     figurine
    0.75
     qualitatively
    0.74
     addictive
    0.74
     consequently
    0.71
     discontinuation
    0.71
     humidifier
    0.71
    Activations Density 0.000%

    No Known Activations