© 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. 58286
    Prev
    Next
    INDEX
    Explanations

    names and 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
    Not in Any Lists

    No Comments

    Negative Logits
    性质
    -2.34
     develop
    -2.34
    并将
    -2.27
    :
    -2.27
     February
    -2.27
     allow
    -2.22
     demonstrate
    -2.20
     staunch
    -2.19
     groundbreaking
    -2.19
     Also
    -2.19
    POSITIVE LOGITS
    ul
    3.06
    ꜆
    3.05
    2
    2.78
    E
    2.66
    しゃぶ
    2.63
    刄
    2.61
     niedersachsen
    2.58
    ⩕
    2.56
    踽
    2.55
    bu
    2.47
    Activations Density 0.067%

    No Known Activations