© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86020
    Prev
    Next
    INDEX
    Explanations

    send email or resume

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

    The neuron fires on directives to send or direct communications (e.g. “send … to” or “be directed to”), i.e. instructions for submitting emails, documents, inquiries, 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_10/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
    苼
    -1.76
    ↵↵↵
    -1.47
     europé
    -1.36
     genero
    -1.36
     puse
    -1.33
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.30
    çs
    -1.30
    inerario
    -1.29
     continúas
    -1.27
     negar
    -1.27
    POSITIVE LOGITS
     to
    2.39
     wystarczy
    1.48
     that
    1.38
     ľah
    1.37
     skuto
    1.30
     gdyby
    1.30
    1
    1.29
     or
    1.24
     všetky
    1.23
     quaisquer
    1.22
    Activations Density 0.016%

    No Known Activations