© 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. 6777
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific entities

    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
     "-
    -2.44
     или
    -2.38
    または
    -2.34
    р
    -2.25
     —
    -2.25
    ！"
    -2.23
     continúas
    -2.13
    ن
    -2.11
    \_
    -2.09
    หรือ
    -2.09
    POSITIVE LOGITS
    s
    2.77
    砗
    2.64
    唞
    2.30
    髏
    2.28
     يساعد
    2.14
    珰
    2.13
    zeichnung
    2.11
     Erfüllung
    2.08
    棪
    2.05
    irical
    2.00
    Activations Density 0.002%

    No Known Activations