© 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. 45240
    Prev
    Next
    INDEX
    Explanations

    describing a person's role or history

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

    The neuron fires on copular and related auxiliary verbs (especially “is,” “was,” “has,” etc.) that introduce biographical or definitional statements about a person.

    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
     покупке
    -1.48
    (!__
    -1.35
    <bos>
    -1.32
    initWithFrame
    -1.30
     เพื่อ
    -1.27
    UTIVE
    -1.25
    孑
    -1.23
    ݣ
    -1.22
    それに
    -1.20
     innumerable
    -1.19
    POSITIVE LOGITS
     who
    1.46
     quiera
    1.38
     rám
    1.31
     גם
    1.27
     malheur
    1.27
    tably
    1.21
     originally
    1.19
     gyrus
    1.17
    ooooo
    1.16
    \
    1.16
    Activations Density 0.086%

    No Known Activations