© 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. 22-GEMMASCOPE-RES-131K
    7. 146
    Prev
    Next
    INDEX
    Explanations

    asking for input

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

    The neuron fires on direct solicitations or invitations—phrases asking the reader for feedback, help, support, or donations.

    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
     also
    -1.17
    Приготовление
    -1.08
     other
    -1.05
     kutoka
    -0.94
     THEN
    -0.93
     länder
    -0.92
     slovens
    -0.90
    ÜN
    -0.90
     ALSO
    -0.89
    を持つ
    -0.89
    POSITIVE LOGITS
     please
    1.51
     Please
    1.38
    Please
    1.38
     joten
    1.23
     so
    1.15
     click
    1.09
     febrero
    1.06
    你可以
    1.03
     you
    1.02
     contact
    1.02
    Activations Density 0.031%

    No Known Activations