© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38354
    Prev
    Next
    INDEX
    Explanations

    tickets, scholarships, codes, memberships

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

    The neuron detects mentions of awarded or given‐away items or promotions (e.g. tickets, scholarships, cards, codes, certificates, memberships, tags).

    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
    _
    -1.55
    f
    -1.39
    y
    -1.16
    b
    -1.13
     it
    -1.10
    k
    -1.07
     if
    -1.05
     солнце
    -1.03
     decorados
    -1.02
     fiecare
    -1.02
    POSITIVE LOGITS
     for
    2.28
     to
    2.11
     для
    1.45
    lblNewLabel
    1.16
    мне
    1.13
     油画
    1.11
    БИ
    1.10
    blurRadius
    1.09
     remon
    1.08
     kişilik
    1.08
    Activations Density 0.043%

    No Known Activations