© 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. 47369
    Prev
    Next
    INDEX
    Explanations

    completed actions or studies

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

    The neuron responds to occurrences of past‐tense “be” auxiliaries (especially “was” and “were”) signaling passive‐voice descriptions of experimental or methodological actions.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     creada
    -0.98
    をしました
    -0.95
     Created
    -0.90
    晰
    -0.88
    álogos
    -0.87
    joit
    -0.86
    をします
    -0.86
     Worked
    -0.85
     creado
    -0.85
     Работа
    -0.84
    POSITIVE LOGITS
     performed
    4.09
     conducted
    3.66
     انجام
    3.42
     perform
    2.86
    performed
    2.66
     carried
    2.66
     done
    2.64
     conduct
    2.53
    conducted
    2.45
     przeprowad
    2.44
    Activations Density 0.142%

    No Known Activations