© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75199
    Prev
    Next
    INDEX
    Explanations

    followed by button/Targeted/applicable/decreased/of/me

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

    The neuron activates on double-quote characters (").

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Often
    -1.97
     oftentimes
    -1.96
     viera
    -1.90
     commonly
    -1.87
     by
    -1.87
    だからこそ
    -1.85
     every
    -1.84
     perpetually
    -1.83
     frequently
    -1.83
     gets
    -1.83
    POSITIVE LOGITS
     protože
    2.13
     and
    2.06
    向けの
    2.00
    様な
    1.95
     chociaż
    1.88
     Dinas
    1.86
     embalaje
    1.85
    ごとの
    1.84
     produjo
    1.83
     encontraba
    1.78
    Activations Density 0.000%

    No Known Activations