© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67436
    Prev
    Next
    INDEX
    Explanations

    sequences after "after"

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

    This neuron fires specifically on the word “After” when it appears (typically as a sentence-initial transition).

    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
    8
    -2.50
    A
    -2.41
     has
    -2.34
    K
    -2.30
     زیرا
    -2.25
    4
    -2.23
     happenings
    -2.16
    5
    -2.11
    in
    -2.09
    en
    -2.09
    POSITIVE LOGITS
    鹩
    2.98
    蓠
    2.22
    nocení
    2.19
    ⑊
    2.14
     که
    2.09
    鸶
    2.08
    ContentAlignment
    2.05
     \
    2.03
    獃
    2.02
    镠
    1.97
    Activations Density 0.028%

    No Known Activations