© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71986
    Prev
    Next
    INDEX
    Explanations

    default values

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

    The neuron fires on code‐related “default” or core identifier tokens (e.g. Default/DEFAULT, default parts, init, api) that signal default settings or standard module/namespace names.

    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
     and
    -2.16
    AutoresizingMask
    -1.64
    鹛
    -1.57
     科技
    -1.52
    ႐
    -1.49
     剑
    -1.48
     功效
    -1.48
     Of
    -1.46
     -
    -1.45
     bahkan
    -1.44
    POSITIVE LOGITS
    isation
    1.77
     wiedzy
    1.69
    abaikan
    1.66
     нового
    1.63
     organisational
    1.56
    🩴
    1.53
    ʼ
    1.53
    durante
    1.51
     souha
    1.50
    sessionStorage
    1.48
    Activations Density 0.001%

    No Known Activations