© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 3065
    Prev
    Next
    INDEX
    Explanations

    ```python` code snippets

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

    The neuron fires strongly on the “appeared first on” attribution phrase that credits a post’s original publication source.

    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
    ﻴ
    1.00
    ov
    0.97
    unlock
    0.89
    iz
    0.88
    iam
    0.87
    transactions
    0.85
    am
    0.85
    ot
    0.85
    ata
    0.85
    estation
    0.84
    POSITIVE LOGITS
    രുന്നു
    0.90
    י
    0.90
    с
    0.89
    т
    0.88
    сль
    0.86
    нит
    0.84
     আমরা
    0.84
    листи
    0.84
     FontWeight
    0.83
    й
    0.83
    Activations Density 0.000%

    No Known Activations