© 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. 14484
    Prev
    Next
    INDEX
    Explanations

    Eventbrite, calendar, Dailymotion, Udemy, Mailchimp

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

    The neuron fires on occurrences of well‐known web service or technology brand names (e.g. Eventbrite, UniProt, DailyMotion, Udemy, Mailchimp, GoDaddy, 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
     has
    -2.03
     If
    -1.65
    A
    -1.60
     jika
    -1.53
     and
    -1.53
     &
    -1.50
     When
    -1.48
     longstanding
    -1.48
     such
    -1.47
    When
    -1.47
    POSITIVE LOGITS
     eſſ
    2.08
    ឵
    1.95
     valentín
    1.84
    킁
    1.84
    ஂ
    1.81
    踅
    1.74
     analis
    1.70
     navidad
    1.70
     frança
    1.68
     golos
    1.68
    Activations Density 0.052%

    No Known Activations