© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25928
    Prev
    Next
    INDEX
    Explanations

    creation and features

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

    The neuron strongly activates on standalone punctuation and numeric tokens—especially periods, hyphens, and digits.

    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
     които
    -1.50
     которые
    -1.48
     такъ
    -1.38
     която
    -1.23
     cewek
    -1.16
     которой
    -1.15
     there
    -1.14
     vytvá
    -1.13
     Gründung
    -1.13
     тях
    -1.13
    POSITIVE LOGITS
     designed
    1.73
     produced
    1.68
     featuring
    1.63
     created
    1.59
     regarded
    1.54
     comprised
    1.52
     made
    1.48
     equipped
    1.45
     conceived
    1.43
     located
    1.38
    Activations Density 0.266%

    No Known Activations