© 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. 69221
    Prev
    Next
    INDEX
    Explanations

    start of quoted speech

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

    The neuron is highly sensitive to numeric tokens—detecting numbers, statistics, dates, and similar quantitative expressions in the text.

    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
     ihrer
    -1.20
     homicidio
    -1.16
     snel
    -1.14
     zes
    -1.05
    olge
    -1.05
     generally
    -1.04
     mempelajari
    -1.04
    解釋
    -1.03
    왕
    -1.02
     zwarte
    -1.01
    POSITIVE LOGITS
     today
    1.26
     our
    1.18
     I
    1.17
     my
    1.16
     your
    1.13
    dă
    1.11
     haters
    1.10
     will
    1.08
     you
    1.05
     tomorrow
    1.04
    Activations Density 0.027%

    No Known Activations