© 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. 33725
    Prev
    Next
    INDEX
    Explanations

    Portuguese and Spanish phrasing and grammar

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

    This neuron picks out the main content word at the start of a user’s question (the key query term) across different languages.

    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
     our
    -1.42
     an
    -1.31
     their
    -1.27
     your
    -1.26
     at
    -1.25
     this
    -1.23
    </h3>
    -1.20
     a
    -1.17
     my
    -1.16
     with
    -1.16
    POSITIVE LOGITS
     magasiner
    1.38
    忤
    1.37
     offrir
    1.32
     niks
    1.32
    voyez
    1.31
     сумка
    1.26
    має
    1.25
    onaise
    1.25
     activos
    1.23
     ſi
    1.23
    Activations Density 0.001%

    No Known Activations