© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127694
    Prev
    Next
    INDEX
    Explanations

    names and brands

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

    The neuron primarily activates on capitalized named entities (proper nouns).

    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
     でも
    -2.59
    It
    -2.44
    )?
    -2.23
    是
    -2.19
     bukanlah
    -2.13
     Those
    -2.11
     Putting
    -2.08
    That
    -2.06
    ꦱ
    -2.05
     spru
    -2.03
    POSITIVE LOGITS
    嵛
    2.84
     deft
    2.56
    等我
    2.55
     în
    2.53
    of
    2.52
     his
    2.42
     самых
    2.39
     atteindre
    2.34
    哙
    2.33
     в
    2.25
    Activations Density 0.017%

    No Known Activations