© 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. 868
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on uncommon, content-bearing words and entities (i.e. low-frequency, information-rich tokens).

    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
    0.67
    ֥
    0.66
    ppure
    0.64
     Приступљено
    0.62
    <()>
    0.61
     ಏಕೆ
    0.60
    렸다
    0.59
     یې
    0.59
     freaking
    0.58
    嘿
    0.58
    POSITIVE LOGITS
    ;,
    2.02
    ，
    1.95
    ،
    1.95
    ;
    1.93
    했고
    1.91
    었고
    1.87
    ፣
    1.87
    ၊
    1.84
     และ
    1.79
     ،
    1.75
    Activations Density 9.668%

    No Known Activations