© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113700
    Prev
    Next
    INDEX
    Explanations

    Grid, jQuery, UI, programming context

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

    code related to UI grids and data tables, particularly their properties, methods, and configuration settings.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects numeric literals (numbers and measurements) 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_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
    Lähde
    -1.68
     oxígeno
    -1.55
    Läh
    -1.48
    ﻲ
    -1.48
     เรา
    -1.44
    絝
    -1.35
    zestaw
    -1.34
    兩人
    -1.33
     hogares
    -1.33
    two
    -1.30
    POSITIVE LOGITS
     проблем
    1.59
    ным
    1.46
     «
    1.40
     даже
    1.34
     sollen
    1.27
    шь
    1.26
    Д
    1.25
    ):
    1.24
     вместо
    1.24
     werden
    1.23
    Activations Density 0.031%

    No Known Activations