© 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. 22-GEMMASCOPE-RES-131K
    7. 64451
    Prev
    Next
    INDEX
    Explanations

    al-Qaida, VOA, international news

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     our
    -1.01
    žiť
    -0.99
    殲
    -0.98
     their
    -0.97
     дів
    -0.94
     }).
    -0.91
     onlyOwner
    -0.91
     #:
    -0.91
     delantero
    -0.90
    なんですね
    -0.90
    POSITIVE LOGITS
     vė
    1.04
    VOA
    1.00
     jį
    1.00
     celta
    0.97
    cherichia
    0.96
    ICLE
    0.94
    kirakan
    0.93
    erevan
    0.93
     ניתן
    0.92
     ziemi
    0.92
    Activations Density 0.008%

    No Known Activations