© 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. 73688
    Prev
    Next
    INDEX
    Explanations

    expresses desired action

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

    The neuron detects occurrences of the root “quer/quier,” i.e. the verb “to want” in Spanish and Portuguese.

    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
     wichtigste
    -2.61
     để
    -2.52
    '
    -2.47
    巨大的
    -2.42
     двумя
    -2.38
    kę
    -2.36
     soo
    -2.34
    觧
    -2.31
     \
    -2.30
    与此同时
    -2.25
    POSITIVE LOGITS
    ᠂
    2.58
    齶
    2.44
    alakip
    2.34
    颺
    2.33
     he
    2.31
    者が
    2.22
    椟
    2.16
    鹚
    2.14
    🪆
    2.14
     что
    2.13
    Activations Density 0.003%

    No Known Activations