© 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. 40198
    Prev
    Next
    INDEX
    Explanations

    effective dates, immediately

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

    The neuron consistently lights up on the token “effective,” i.e. it detects statements of effective dates or timing.

    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
     '
    -2.59
     \"
    -2.53
     нескольких
    -2.33
     `
    -2.23
     „
    -2.22
     ۶
    -2.22
     '[
    -2.17
     ´
    -2.03
     wist
    -1.99
      
    -1.98
    POSITIVE LOGITS
    Despite
    2.47
    ൎ
    2.45
    مواد
    2.42
    Although
    2.41
    Because
    2.41
    Since
    2.38
    While
    2.36
    However
    2.31
    摃
    2.28
    ･･
    2.27
    Activations Density 0.009%

    No Known Activations