© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38572
    Prev
    Next
    INDEX
    Explanations

    What comes next

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

    The neuron fires on question indicators—most strongly on the question mark “?” (and secondarily on “What”).

    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
     to
    -1.31
     when
    -1.27
     in
    -1.20
     by
    -1.07
     on
    -1.04
     that
    -1.03
    eará
    -1.03
     但是
    -1.02
     It
    -1.01
     so
    -0.99
    POSITIVE LOGITS
     demostr
    1.13
     tambin
    1.13
    commented
    1.11
     appris
    1.05
     hias
    1.05
    Recomend
    1.05
     đừng
    1.04
     zobac
    1.04
     herramientas
    1.02
    kleidung
    1.02
    Activations Density 0.034%

    No Known Activations