© 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. 10-GEMMASCOPE-RES-131K
    7. 39948
    Prev
    Next
    INDEX
    Explanations

    between two items

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

    The neuron specifically fires on the very last content token of each text segment, marking segment‐end words.

    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
     моего
    -1.52
     in
    -1.49
    🡺
    -1.38
    assword
    -1.34
     azonban
    -1.32
     lidí
    -1.27
     älteren
    -1.27
    ätzliche
    -1.26
    kolen
    -1.26
     vă
    -1.25
    POSITIVE LOGITS
    拉克
    1.65
    m
    1.58
     工事
    1.55
    At
    1.53
     condiv
    1.52
    v
    1.52
     aforesaid
    1.50
     esist
    1.50
     "",
    1.49
    maakt
    1.47
    Activations Density 0.024%

    No Known Activations