© 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. 67508
    Prev
    Next
    INDEX
    Explanations

    di- prefix

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

    This neuron is a general affix detector—it lights up on common small morphemes (e.g. prefixes like di-, un-, and suffixes like ‑ed, ‑able) wherever they occur.

    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
    ཌ
    -1.66
     colossal
    -1.65
    could
    -1.55
     dando
    -1.53
     flamboyant
    -1.52
     horrid
    -1.51
     overly
    -1.51
     هذا
    -1.47
    !!!!!!!
    -1.46
     !!!!
    -1.45
    POSITIVE LOGITS
     by
    2.55
     any
    1.92
     invigor
    1.89
     fifteen
    1.88
     eight
    1.88
     Although
    1.84
     Since
    1.83
     those
    1.82
     revital
    1.81
     noticeably
    1.80
    Activations Density 0.043%

    No Known Activations