© 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. 85402
    Prev
    Next
    INDEX
    Explanations

    names with III suffix

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

    The neuron detects generational name suffixes (e.g., “III,” “Jr.”).

    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
    </b>
    -1.68
     cœurs
    -1.55
    --
    -1.54
     konusunda
    -1.54
    despite
    -1.51
     oignon
    -1.50
     gezet
    -1.45
     PROBLE
    -1.44
    ㈲
    -1.41
     corações
    -1.39
    POSITIVE LOGITS
     who
    2.38
     would
    1.50
    ческими
    1.42
    等人
    1.38
     wegen
    1.38
     had
    1.37
     more
    1.33
     после
    1.32
     \
    1.27
     After
    1.27
    Activations Density 0.021%

    No Known Activations