© 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. 32579
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    ּוֹ
    -1.13
    ִּ
    -1.08
    登记
    -1.03
    ֶּ
    -1.01
     optimistic
    -0.98
    lapsingToolbar
    -0.98
    ugget
    -0.98
    rieved
    -0.96
    ַּ
    -0.96
    哧
    -0.95
    POSITIVE LOGITS
     նաև
    1.21
     mentales
    1.20
    parece
    1.19
     hadapan
    1.18
    prender
    1.18
    ସ
    1.17
     chré
    1.15
     även
    1.14
    también
    1.13
    SMP
    1.10
    Activations Density 0.044%

    No Known Activations