© 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. 99343
    Prev
    Next
    INDEX
    Explanations

    recons + titute/olidation

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

    The neuron fires on tokens beginning with the “recons-” string (as in reconstitute, reconsolidation, reconsidered, etc.).

    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
    玙
    -2.77
     have
    -2.34
    Ꭳ
    -2.30
    ଽ
    -2.30
     greateſt
    -2.23
    愿望
    -2.22
     所以
    -2.17
     喜欢
    -2.17
    蜻
    -2.16
     positiven
    -2.11
    POSITIVE LOGITS
    ’
    4.09
    絰
    2.80
    i
    2.64
    糴
    2.44
     dotyczące
    2.33
    緜
    2.31
    '&
    2.30
     hábiles
    2.30
    ')
    2.23
    田村
    2.22
    Activations Density 0.024%

    No Known Activations