© 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. 67127
    Prev
    Next
    INDEX
    Explanations

    words starting with dis-

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

    The neuron fires on the substring “dis” (i.e. the dis- prefix) wherever it occurs at the start of a word.

    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
    嵛
    -3.30
     áudio
    -2.61
    cinoma
    -2.58
    薷
    -2.55
    いずれ
    -2.52
     ícone
    -2.50
     beginning
    -2.50
     farther
    -2.45
    黑衣
    -2.45
    莇
    -2.44
    POSITIVE LOGITS
    }
    2.84
    0
    2.72
    ).
    2.63
    3
    2.44
    ﻊ
    2.39
    e
    2.31
    2.27
     is
    2.23
    ные
    2.19
     für
    2.14
    Activations Density 0.076%

    No Known Activations