© 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. 12791
    Prev
    Next
    INDEX
    Explanations

    special characters and keywords

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

    This neuron fires on colon tokens (the “:” punctuation) in code or templates.

    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
     pérd
    -1.27
     ハーフ
    -1.13
     madeira
    -1.13
     certamente
    -1.12
    ......”
    -1.12
     suscit
    -1.08
     recentemente
    -1.08
     applau
    -1.07
    ῞
    -1.06
     migliorare
    -1.04
    POSITIVE LOGITS
     in
    1.17
     with
    1.17
     now
    1.12
     on
    1.12
     --
    1.07
     ---
    1.07
     extraña
    1.06
    ).
    1.05
     ifrån
    1.02
     into
    1.01
    Activations Density 0.004%

    No Known Activations