© 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. 22-GEMMASCOPE-RES-131K
    7. 73084
    Prev
    Next
    INDEX
    Explanations

    first name and surname

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find named entities representing people’s full names.

    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
    踯
    -1.09
    :
    -1.05
     hermes
    -1.04
    Adds
    -1.03
    xii
    -1.03
     Launches
    -1.03
    っていない
    -1.02
    抱怨
    -1.02
     コスメ
    -1.00
     sarebbe
    -0.99
    POSITIVE LOGITS
     will
    1.45
     has
    1.41
     with
    1.34
    Beskrivning
    1.15
     and
    1.11
    Kuva
    1.09
     went
    1.08
     is
    1.05
     we
    1.05
    <?
    1.03
    Activations Density 0.018%

    No Known Activations