© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8986
    Prev
    Next
    INDEX
    Explanations

    pay attention

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

    The neuron fires on main action verbs—lexical verbs (e.g. played, show, assigned, providing) that denote the primary events or activities in the text.

    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
     pliers
    1.04
     catastrophes
    1.03
     vulgaris
    1.00
    worthiness
    0.99
     disasters
    0.98
     incomes
    0.97
    lands
    0.95
    ﻄ
    0.95
     cucumbers
    0.94
    ov
    0.94
    POSITIVE LOGITS
    廻
    0.99
     credence
    0.97
    على
    0.94
    ↵
    0.93
     রেখে
    0.91
    Flower
    0.89
    хову
    0.89
     название
    0.88
    ه
    0.88
    Snapshot
    0.87
    Activations Density 1.123%

    No Known Activations