© 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. 113875
    Prev
    Next
    INDEX
    Explanations

    android or html alignment attributes

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

    the word "align" in code, particularly in Android XML layouts and configuration files.

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

    This neuron detects alignment-related attribute names (e.g. “gravity” or “align”) in code.

    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
     heuti
    -1.37
     nonexistent
    -1.36
    りましたが
    -1.34
     !_
    -1.32
     and
    -1.30
     ewigen
    -1.27
     الحدود
    -1.27
    r
    -1.27
     dotyczą
    -1.25
    </em>
    -1.24
    POSITIVE LOGITS
    ଢ
    1.67
    MenuInflater
    1.66
    "},
    1.54
    ႐
    1.54
    ༷
    1.52
    ޞ
    1.49
    ёх
    1.48
    setzer
    1.45
     importants
    1.45
    ICKEN
    1.45
    Activations Density 0.008%

    No Known Activations