© 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. 72060
    Prev
    Next
    INDEX
    Explanations

    palestine, nuremberg, africa, ireland, java, usb

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    From
    -2.20
    Not
    -2.06
    Also
    -2.03
    Surprisingly
    -2.03
    For
    -1.95
    One
    -1.95
    Only
    -1.92
     our
    -1.85
    Like
    -1.84
    Just
    -1.84
    POSITIVE LOGITS
    蠓
    2.63
    蛲
    2.48
    🫃
    2.20
    ⎔
    2.20
    穑
    2.14
    𓁹
    2.13
    稣
    2.06
    摀
    2.05
    
    2.03
    殽
    2.03
    Activations Density 0.396%

    No Known Activations