© 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. 47182
    Prev
    Next
    INDEX
    Explanations

    approximation and investigation

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

    This neuron detects past-participial or perfect/passive-voice constructions (e.g. "is known," "have been measured," "related," etc.).

    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
     officiellement
    -1.08
    schuhe
    -0.96
     официаль
    -0.94
    edoc
    -0.94
     ermittelt
    -0.94
    Adjustment
    -0.88
     Herbal
    -0.88
     researching
    -0.86
     IUser
    -0.86
    astronomie
    -0.86
    POSITIVE LOGITS
    cripción
    1.04
     Perhaps
    1.00
    誨
    0.99
     ingrédients
    0.96
     スイーツ
    0.96
     loopholes
    0.95
    ينج
    0.94
    Indeed
    0.93
    Perhaps
    0.93
     beautiful
    0.91
    Activations Density 0.149%

    No Known Activations