© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12558
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on code identifiers—especially variable or constant names (e.g. “child,” “id,” “arrchildid,” etc.) often seen in programming error messages.

    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
    _
    0.79
    -
    0.68
    _(
    0.62
    \_
    0.61
    </em>
    0.59
     një
    0.58
    -‘
    0.57
     actúa
    0.57
    Ĝ
    0.56
    </h5>
    0.55
    POSITIVE LOGITS
     {},
    0.64
    ल्स
    0.60
    σης
    0.59
    せず
    0.58
    atres
    0.57
    нор
    0.57
    рім
    0.57
    しも
    0.56
    ﻥ
    0.56
    ре
    0.55
    Activations Density 0.064%

    No Known Activations