© 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. 9986
    Prev
    Next
    INDEX
    Explanations

    return codes

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

    the neuron is selectively activating on numeric tokens and other nonstandard Unicode symbols (i.e. numbers and odd character sequences) 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_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
     verwenden
    0.93
     möchten
    0.83
    𝐖
    0.82
    in
    0.81
     PAOK
    0.80
     emoc
    0.80
     istek
    0.79
     vezes
    0.79
     กล่าว
    0.79
    𝑥
    0.78
    POSITIVE LOGITS
     Establishment
    0.67
    сини
    0.65
    Gene
    0.64
    的部分
    0.64
    柳
    0.64
    必然
    0.63
     annals
    0.63
     heretofore
    0.62
    ർഡ്
    0.62
    Netherlands
    0.61
    Activations Density 0.000%

    No Known Activations