© 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. 22-GEMMASCOPE-RES-131K
    7. 14570
    Prev
    Next
    INDEX
    Explanations

    introducing further information

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

    The neuron fires on the discourse marker “Besides.”

    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
     
    -2.22
    ‐
    -2.11
     ”
    -2.03
     unwavering
    -1.96
    IN
    -1.95
     is
    -1.94
     sincere
    -1.93
     and
    -1.92
    к
    -1.90
     partnership
    -1.88
    POSITIVE LOGITS
    秶
    2.53
    They
    2.48
    It
    2.45
    That
    2.41
    This
    2.33
    There
    2.31
     Mijn
    2.27
     اینکه
    2.22
     duele
    2.22
     menging
    2.16
    Activations Density 0.002%

    No Known Activations