© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73958
    Prev
    Next
    INDEX
    Explanations

    forwarding

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

    The neuron detects the verb “forward” (in all its forms: forward, forwarded, forwarding).

    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
    "
    -2.19
    in
    -1.93
    replyreport
    -1.83
    Ｃ
    -1.80
     glaubte
    -1.63
     получится
    -1.63
    invasive
    -1.61
    Figure
    -1.58
     dAtA
    -1.55
    </b>
    -1.54
    POSITIVE LOGITS
     the
    2.23
     Entdecke
    2.20
     Weitere
    2.20
    diseño
    2.03
     Welche
    1.97
    
    1.96
    萏
    1.91
    烀
    1.89
     Alquiler
    1.87
     Resolución
    1.87
    Activations Density 0.013%

    No Known Activations