© 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. 2816
    Prev
    Next
    INDEX
    Explanations

    ending punctuation after specific words

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

    The neuron fires on high-information content words—especially specific nouns, names, and quoted terms—i.e. rare or salient tokens rather than common function words.

    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
     }.
    1.27
    }.
    1.08
    '].
    1.04
     "".
    1.03
    ].
    1.02
     ].
    1.02
    "/>.
    0.98
    ').
    0.98
    ().
    0.97
    '$.
    0.96
    POSITIVE LOGITS
    ,”
    2.78
    ,"
    2.61
    ,’’
    2.58
    ,''
    2.53
    ,»
    2.44
    ,\"
    2.41
    ),”
    2.33
    ，”
    2.23
    ],”
    2.22
    .,"
    2.20
    Activations Density 0.343%

    No Known Activations