© 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. 22-GEMMASCOPE-RES-131K
    7. 15104
    Prev
    Next
    INDEX
    Explanations

    committed enough

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

    The neuron detects direct second-person calls to action or self-help/marketing prompts (e.g. “Do you want to…?”, “be proactive in protecting yourself,” 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_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
    ところは
    -1.16
    のですが
    -1.14
    excellents
    -1.07
    irce
    -1.06
    地说道
    -1.05
     perfeito
    -1.03
     acoged
    -1.01
     respetu
    -1.01
     рік
    -1.01
    buatan
    -1.01
    POSITIVE LOGITS
    を
    1.05
    それにしても
    0.97
    LAHOMA
    0.93
    )•
    0.93
    iest
    0.90
     $
    0.90
     dugaan
    0.90
    äs
    0.87
    \#:
    0.86
     Europas
    0.86
    Activations Density 0.130%

    No Known Activations