© 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. 34-GEMMASCOPE-RES-131K
    7. 25873
    Prev
    Next
    INDEX
    Explanations

    `getExternalStorage` directory

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

    The neuron responds to tokens containing non-alphanumeric punctuation—especially apostrophes in contractions (e.g. “manager’s,” “isn’t,” “it’s,” “haven’t”) and other special symbols.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Atención
    -1.17
     водитель
    -1.01
     plaintiffs
    -1.01
     COMPLE
    -1.00
    Stap
    -0.99
    ｕ
    -0.98
     EXCLUS
    -0.98
     fameux
    -0.98
    Matin
    -0.96
     hashMap
    -0.96
    POSITIVE LOGITS
     or
    1.24
     your
    1.11
     most
    1.08
     during
    1.08
     Being
    1.04
     should
    1.01
     Even
    0.99
     It
    0.98
     intended
    0.98
     even
    0.97
    Activations Density 0.147%

    No Known Activations