© 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. 68569
    Prev
    Next
    INDEX
    Explanations

    place names with "heights"

    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
    1
    -3.50
    0
    -2.88
    ed
    -2.66
    2
    -2.66
    我覺得
    -2.41
     aktualisiert
    -2.39
    u
    -2.34
    為什麼
    -2.31
    new
    -2.28
    揼
    -2.22
    POSITIVE LOGITS
    出了一
    2.63
    野外
    2.55
     Heights
    2.48
     But
    2.47
    縞
    2.44
     You
    2.39
    あります
    2.38
    部分は
    2.23
     Gets
    2.22
    阄
    2.22
    Activations Density 0.002%

    No Known Activations