© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 760
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs before nouns/verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ではまた
    -1.73
    余談
    -1.73
    おわりに
    -1.68
    次回は
    -1.61
     últimas
    -1.57
    ハロウィン
    -1.48
     divino
    -1.47
    ждением
    -1.47
     Certifications
    -1.45
    >>
    -1.43
    POSITIVE LOGITS
    </b>
    1.69
     %.
    1.46
    kadın
    1.43
    huevos
    1.41
     jedynie
    1.40
    pozdrawiam
    1.39
     which
    1.39
    carteles
    1.38
     Much
    1.37
    consejos
    1.33
    Activations Density 0.025%

    No Known Activations