© 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. 32875
    Prev
    Next
    INDEX
    Explanations

    along or on a street

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Autres
    -1.07
    랍
    -1.03
     teléfono
    -1.03
    ัตว์
    -1.02
    vantaged
    -1.00
    others
    -1.00
     graisse
    -1.00
    瀞
    -1.00
    สิ่ง
    -0.99
    歘
    -0.98
    POSITIVE LOGITS
     on
    1.50
     street
    1.27
     novios
    1.20
     both
    1.18
     hebdomada
    1.15
     voluntarios
    1.08
     tornillos
    1.04
     Street
    1.02
     these
    1.01
     känns
    0.99
    Activations Density 0.026%

    No Known Activations