© 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. 8471
    Prev
    Next
    INDEX
    Explanations

    kon, kor, ok, Ek, pro, kom, kur, Ok, disk

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

    The neuron strongly activates on tokens that begin with or contain common Latin‐derived prefixes (e.g. “pro-,” “con-/com-/cor-,” “form-”) typical of formal or technical terms.

    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
     It
    -2.91
     I
    -2.61
     “
    -2.55
     They
    -2.27
     You
    -2.27
     have
    -2.16
     was
    -2.13
     Its
    -2.08
     This
    -2.08
         
    -2.08
    POSITIVE LOGITS
    珢
    2.83
    ܜ
    2.52
    ụp
    2.45
     baskılı
    2.44
    壟
    2.31
    ⸰
    2.22
    鐒
    2.20
     görüntüsü
    2.17
     görüntüleri
    2.17
     botas
    2.17
    Activations Density 0.009%

    No Known Activations