© 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. 6618
    Prev
    Next
    INDEX
    Explanations

    emoticons and punctuation ending phrases

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

    The neuron is highly sensitive to standalone punctuation tokens—especially colons (often in timestamps or emoticon-like constructs).

    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
     dy
    0.61
    ...\
    0.57
     li
    0.55
     sau
    0.55
     ihe
    0.55
     oi
    0.55
     naar
    0.54
    }{$\
    0.54
     ral
    0.53
     ue
    0.52
    POSITIVE LOGITS
    ))
    1.33
    -)
    1.31
    )))
    1.20
    ))))
    1.20
     ))
    1.10
    ^)
    1.06
    )))))
    1.06
     )))
    1.05
    )).
    1.05
    ))^{
    1.05
    Activations Density 0.086%

    No Known Activations