© 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. 72053
    Prev
    Next
    INDEX
    Explanations

    magazine content

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

    The neuron activates on occurrences of the word “magazine,” especially when it appears as part of publication titles.

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

    No Comments

    Negative Logits
    埽
    -3.00
    轳
    -2.97
    甃
    -2.95
    擼
    -2.92
    𖣘
    -2.78
    瞜
    -2.66
     hefty
    -2.64
     VERY
    -2.64
    
    -2.63
     amazingly
    -2.56
    POSITIVE LOGITS
    e
    2.47
    .
    2.38
    d
    2.23
    <bos>
    2.22
    Ironically
    2.19
     получила
    2.17
     facilitates
    2.16
    いです
    2.14
    Surprisingly
    2.13
     adicionales
    2.11
    Activations Density 0.006%

    No Known Activations