© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11909
    Prev
    Next
    INDEX
    Explanations

    The neuron flags tokens that look like technical model or file identifiers—uppercase letter sequences often mixed with digits.

    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
    >>();
    0.58
     novità
    0.57
     elastomers
    0.56
    ্টর
    0.55
     concor
    0.55
    пом
    0.54
    TECH
    0.54
    ёв
    0.54
    elling
    0.53
     stvar
    0.53
    POSITIVE LOGITS
     S
    0.86
    ylvan
    0.82
    ometime
    0.79
    ocratic
    0.74
    S
    0.68
     Sgt
    0.67
    rir
    0.67
    eltzer
    0.67
     sizz
    0.66
    maxage
    0.66
    Activations Density 0.325%

    No Known Activations