© 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. 7065
    Prev
    Next
    INDEX
    Explanations

    account registration or joining

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

    The neuron strongly activates on forum “registration” and “guest” prompts—that is, words urging or requiring users to register or join before posting or gaining access.

    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
    INCLUD
    -0.82
     искусство
    -0.82
    krim
    -0.81
     pracu
    -0.80
    Mc
    -0.80
     покра
    -0.77
    čiť
    -0.77
    Instead
    -0.76
     art
    -0.76
    blobs
    -0.74
    POSITIVE LOGITS
     registration
    2.77
     registering
    2.70
     register
    2.67
     Register
    2.44
    register
    2.33
    注册
    2.25
    Register
    2.22
     REGISTER
    2.19
    登録
    2.16
     registered
    2.14
    Activations Density 0.109%

    No Known Activations