© 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. 39136
    Prev
    Next
    INDEX
    Explanations

    middle name or initial

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

    The neuron strongly activates on the word “middle” (and its substrings) as used in “middle name” contexts.

    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
     all
    -1.30
     an
    -1.19
    an
    -1.16
     What
    -1.12
    le
    -1.10
     in
    -1.09
     any
    -1.09
     on
    -1.07
     our
    -1.07
     Many
    -1.06
    POSITIVE LOGITS
     právě
    1.37
     représenter
    1.30
    Occasionally
    1.22
     yalnız
    1.22
     poesía
    1.19
     nyní
    1.19
     meistens
    1.16
    führt
    1.13
    uthor
    1.11
    celain
    1.11
    Activations Density 0.000%

    No Known Activations