© 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. 67050
    Prev
    Next
    INDEX
    Explanations

    Portuguese and Russian phrases

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

    This neuron activates on the occurrences of the preposition “para” in Spanish/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_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
    <bos>
    -3.33
    そして
    -2.33
    方針
    -2.22
    などが
    -2.13
    延伸閱讀
    -2.11
    主键
    -2.11
    見
    -2.08
    潆
    -2.02
    もあります
    -1.95
     pró
    -1.93
    POSITIVE LOGITS
    逦
    2.41
    тся
    2.20
    ところに
    2.16
    際に
    2.16
     Erwachsene
    2.14
    蘧
    2.14
    にします
    2.11
     the
    2.03
    たまた
    2.02
    вості
    2.00
    Activations Density 0.004%

    No Known Activations