© 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. 81237
    Prev
    Next
    INDEX
    Explanations

    states followed by verbs

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

    The neuron responds most strongly to longer, multi‐syllable content words (e.g. proper names, technical terms, and domain names).

    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
    Exists
    -1.45
     ſt
    -1.38
     ſever
    -1.28
     Allociné
    -1.28
    exists
    -1.27
     daga
    -1.27
    owing
    -1.26
    癱
    -1.23
     EXISTS
    -1.22
     ift
    -1.21
    POSITIVE LOGITS
     is
    3.95
     isn
    3.13
     was
    2.64
     requires
    2.52
     wasn
    2.50
     means
    2.38
     seems
    2.34
     would
    2.28
     seemed
    2.16
     might
    2.08
    Activations Density 0.296%

    No Known Activations