© 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. 22-GEMMASCOPE-RES-131K
    7. 25707
    Prev
    Next
    INDEX
    Explanations

    first occurrences

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

    The neuron flags past-tense verbs and related words used to mark milestones or chronological events in descriptions.

    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
     خواهید
    -0.93
    ulates
    -0.89
     matchs
    -0.85
     abur
    -0.82
    (),
    -0.82
    .",
    -0.81
    蒡
    -0.81
     Monat
    -0.80
    asca
    -0.79
    endency
    -0.77
    POSITIVE LOGITS
     begins
    1.09
     began
    1.05
     first
    0.97
     starts
    0.96
     begin
    0.94
     pertama
    0.94
     Pertama
    0.90
    正式
    0.90
     ขาว
    0.90
    упо
    0.86
    Activations Density 0.119%

    No Known Activations