© 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. 38561
    Prev
    Next
    INDEX
    Explanations

    expressing opinions or direct statements

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

    The neuron fires on emphatic first-person opinion markers and discourse cues (e.g. “honestly,” “frankly,” “I have to say,” “I must admit”).

    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
    =
    -1.52
     was
    -1.28
    B
    -1.27
    T
    -1.26
     sikkert
    -1.23
    ～。
    -1.23
    érieures
    -1.21
    する
    -1.19
    ),
    -1.19
    ご注文
    -1.16
    POSITIVE LOGITS
     zuverläs
    1.36
    since
    1.34
     poderosos
    1.34
    rower
    1.30
    ederal
    1.28
     which
    1.23
    oherty
    1.23
     refroidissement
    1.23
     gefahren
    1.23
    candid
    1.23
    Activations Density 0.027%

    No Known Activations