© 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. 6704
    Prev
    Next
    INDEX
    Explanations

    phrases starting with reasons to

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

    The neuron activates on constructions introducing a “reason(s) to …,” i.e. phrases like “reasons to X” or “one reason to …” that signal listicle or justification headings.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     protectora
    -1.72
     dança
    -1.67
    strona
    -1.66
     illustrious
    -1.66
     daunting
    -1.63
     aislados
    -1.59
     simplistic
    -1.55
     únicos
    -1.55
    ෑ
    -1.53
     ที่
    -1.52
    POSITIVE LOGITS
    "
    2.02
    с
    1.79
    jun
    1.55
    ('
    1.52
     данной
    1.49
    ল
    1.46
    ber
    1.45
     augusti
    1.44
     fusca
    1.43
    -
    1.43
    Activations Density 0.015%

    No Known Activations