© 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. 10-GEMMASCOPE-RES-131K
    7. 102064
    Prev
    Next
    INDEX
    Explanations

    volume or series numbers

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

    The neuron fires on numeric identifiers (e.g. volume, episode, and series numbers) embedded in titles or labels.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     necessary
    -1.39
     these
    -1.39
    Often
    -1.28
     while
    -1.27
     Often
    -1.25
     different
    -1.23
    
    -1.23
     method
    -1.19
     could
    -1.17
     often
    -1.17
    POSITIVE LOGITS
    .”
    1.41
    ?”
    1.20
    ongevity
    1.20
    rolley
    1.15
    ändige
    1.14
     ”
    1.12
    ”
    1.10
    Kh
    1.09
    commodation
    1.09
     février
    1.09
    Activations Density 0.069%

    No Known Activations