© 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. 72226
    Prev
    Next
    INDEX
    Explanations

    not to be published or confused

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

    The neuron detects formal “Not to be published/cited” disclaimer phrases that mark documents as not approved for official publication.

    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
     a
    -1.90
     revelado
    -1.80
     to
    -1.78
    
    -1.74
    曁
    -1.64
     its
    -1.63
    躄
    -1.61
     berücksich
    -1.59
     desmotiv
    -1.58
     are
    -1.53
    POSITIVE LOGITS
    These
    1.71
    <strong>
    1.70
    Some
    1.59
    Only
    1.54
    Should
    1.51
    Perhaps
    1.45
     Cupcakes
    1.44
    Like
    1.41
    When
    1.41
    Unlike
    1.40
    Activations Density 0.013%

    No Known Activations