© 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. 13683
    Prev
    Next
    INDEX
    Explanations

    presenting information or difficulties

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

    The neuron fires on occurrences of the verb “present” (in its various inflected forms such as presented, presenting, or presents).

    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
     deployments
    -0.99
     hiyo
    -0.90
    2
    -0.88
    MENTE
    -0.88
     Después
    -0.87
     frequentemente
    -0.84
     设计
    -0.84
    起来的
    -0.84
     finally
    -0.82
     предыду
    -0.82
    POSITIVE LOGITS
     presents
    1.28
     an
    1.26
     presented
    1.24
     as
    1.12
     a
    1.09
     presentan
    1.07
     information
    1.05
     presenting
    1.05
     presenta
    1.03
    Presenting
    1.03
    Activations Density 0.087%

    No Known Activations