© 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. 106303
    Prev
    Next
    INDEX
    Explanations

    causal identification and estimation

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

    The neuron fires on technical/statistical jargon and code-like tokens (e.g. library names, method names, numeric or all-caps acronyms) typically found in a code block or academic‐methods section.

    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
     Bayesian
    -0.83
     поба
    -0.77
    ̖
    -0.71
    ⠂
    -0.68
    мә
    -0.68
    SOA
    -0.67
    Hierarchical
    -0.66
    Bayesian
    -0.66
     organised
    -0.65
     samochod
    -0.65
    POSITIVE LOGITS
     observational
    0.96
     LATE
    0.95
     causal
    0.88
     Rubin
    0.88
     identification
    0.87
     Robins
    0.84
     crores
    0.84
     estimators
    0.83
     Judea
    0.82
     ATT
    0.81
    Activations Density 0.073%

    No Known Activations