© 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. 34-GEMMASCOPE-RES-131K
    7. 30088
    Prev
    Next
    INDEX
    Explanations

    names following labels

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

    This neuron detects and responds to leading whitespace indentation (i.e. indentation levels) at the start of code lines.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     नी
    -0.80
    varargin
    -0.78
    dessous
    -0.75
     workpiece
    -0.75
    ("*
    -0.74
    subst
    -0.73
     Kirke
    -0.73
     varargin
    -0.73
     Schroeder
    -0.73
    lu
    -0.72
    POSITIVE LOGITS
     perfeito
    0.85
     ارد
    0.81
     Conseils
    0.80
    Cuar
    0.79
    пка
    0.78
    gup
    0.77
     quadru
    0.77
     PROPOSED
    0.77
    Cuad
    0.77
     scopes
    0.76
    Activations Density 0.010%

    No Known Activations