© 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. 33398
    Prev
    Next
    INDEX
    Explanations

    first time

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

    The neuron fires on mentions of “first” occurrences—especially “first time I …” or similar self-reports of doing something for the first time.

    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
    THEY
    -1.00
    madeus
    -0.98
     toni
    -0.98
     MATHEMAT
    -0.98
    ——–
    -0.95
    INGREDIENTS
    -0.94
     geweldig
    -0.94
     misericordia
    -0.94
    Tradu
    -0.93
    コート
    -0.93
    POSITIVE LOGITS
     myself
    1.33
     ever
    1.30
     experience
    1.20
     my
    1.18
     first
    1.16
     EVER
    1.12
    Both
    1.06
    อะไร
    1.04
     siquiera
    1.03
     überhaupt
    1.01
    Activations Density 0.043%

    No Known Activations