© 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. 34-GEMMASCOPE-RES-131K
    7. 58174
    Prev
    Next
    INDEX
    Explanations

    word origins and meanings

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

    The neuron is primarily detecting descriptive adjectives in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     and
    -1.34
    ִּ
    -1.05
     跳转至
    -1.02
    ּוֹ
    -1.00
     và
    -1.00
    のみ
    -0.98
     then
    -0.98
    たびに
    -0.97
    ない
    -0.95
     และ
    -0.94
    POSITIVE LOGITS
     or
    2.66
     или
    1.51
     kimse
    1.45
     oreja
    1.23
     decorados
    1.21
    という意味
    1.20
     یا
    1.20
     pierna
    1.19
    宝物
    1.19
     oneself
    1.16
    Activations Density 0.066%

    No Known Activations