© 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. 4833
    Prev
    Next
    INDEX
    Explanations

    look or get followed by back or started

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

    The neuron fires strongly on bare‐infinitive (dictionary form) action verbs (e.g. “go,” “take,” “look,” “find,” etc.).

    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
    д
    0.85
    лосо
    0.81
    О
    0.80
    ल
    0.78
    cuno
    0.75
     салы
    0.74
    после
    0.73
    ousand
    0.73
    ровать
    0.71
    ồ
    0.71
    POSITIVE LOGITS
     astray
    0.84
     cukup
    0.68
     Boring
    0.67
     Conversely
    0.66
     Adds
    0.66
    OY
    0.66
     Static
    0.66
     Brows
    0.66
     smoothly
    0.65
     dehuman
    0.64
    Activations Density 0.001%

    No Known Activations