© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70345
    Prev
    Next
    INDEX
    Explanations

    membership and clubs

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

    The neuron flags “informational” tokens—things like numbers, punctuation in URLs or web addresses, and brand-style or proper-name tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    CCB
    -0.77
     disorderly
    -0.77
     configur
    -0.77
    cythe
    -0.76
    𝔳
    -0.74
     chop
    -0.72
    gameserver
    -0.71
     thùng
    -0.70
    uels
    -0.69
     igual
    -0.69
    POSITIVE LOGITS
     membership
    1.66
    Membership
    1.59
     club
    1.55
    membership
    1.55
    club
    1.39
     Membership
    1.38
     clubs
    1.34
     CLUB
    1.30
     Club
    1.27
     MEMBERSHIP
    1.23
    Activations Density 0.008%

    No Known Activations